Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
  • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
  • G06F21/55—Detecting local intrusion or implementing counter-measures
  • G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
  • G06F21/561—Virus type analysis
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N20/00—Machine learning
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L63/00—Network architectures or network communication protocols for network security
  • H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
  • H04L63/0227—Filtering policies
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L63/00—Network architectures or network communication protocols for network security
  • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
  • H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
  • H04L63/1416—Event detection, e.g. attack signature detection
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L63/00—Network architectures or network communication protocols for network security
  • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
  • H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
  • H04L63/1425—Traffic logging, e.g. anomaly detection
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L63/00—Network architectures or network communication protocols for network security
  • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
  • H04L63/1441—Countermeasures against malicious traffic
  • H04L63/145—Countermeasures against malicious traffic the attack involving the propagation of malware through the network, e.g. viruses, trojans or worms

Definitions

• Malware is a general term commonly used to refer to malicious software (e.g., including a variety of hostile, intrusive, and/or otherwise unwanted software). Malware can be in the form of code, scripts, active content, and/or other software.
• Example uses of malware include disrupting computer and/or network operations, stealing proprietary information (e.g., confidential information, such as identity, financial, and/or intellectual property related information), and/or gaining access to private/proprietary computer systems and/or computer networks.
• proprietary information e.g., confidential information, such as identity, financial, and/or intellectual property related information
• Unfortunately as techniques are developed to help detect and mitigate malware, nefarious authors find ways to circumvent such efforts. Accordingly, there is an ongoing need for improvements to techniques for identifying and mitigating malware.
• Figure 1 illustrates an example of an environment in which malicious applications are detected and prevented from causing harm.
• Figure 2A illustrates an embodiment of a data appliance.
• Figure 2B is a functional diagram of logical components of an embodiment of a data appliance.
• Figure 3 illustrates an example of logical components that can be included in a system for analyzing samples.
• Figure 4 illustrates portions of an example embodiment of a threat engine.
• Figure 5 illustrates an example of a portion of a tree.
• Figure 6 illustrates an example of a process for performing inline malware detection on a data appliance.
• Figure 7A illustrates an example hash table for a file.
• Figure 7B illustrates an example threat signature for a sample.
• Figure 8A illustrates an example of a process for performing feature extraction.
• Figure 8B illustrates an example of a process for generating a model.
• the invention can be implemented in numerous ways, including as a process; an apparatus; a system; a composition of matter; a computer program product embodied on a computer readable storage medium; and/or a processor, such as a processor configured to execute instructions stored on and/or provided by a memory coupled to the processor.
• these implementations, or any other form that the invention may take, may be referred to as techniques.
• the order of the steps of disclosed processes may be altered within the scope of the invention.
• a component such as a processor or a memory described as being configured to perform a task may be implemented as a general component that is temporarily configured to perform the task at a given time or a specific component that is manufactured to perform the task.
• the term ‘processor’ refers to one or more devices, circuits, and/or processing cores configured to process data, such as computer program instructions.
• a firewall generally protects networks from unauthorized access while permitting authorized communications to pass through the firewall.
• a firewall is typically a device, a set of devices, or software executed on a device that provides a firewall function for network access.
• a firewall can be integrated into operating systems of devices (e.g., computers, smart phones, or other types of network communication capable devices).
• a firewall can also be integrated into or executed as one or more software applications on various types of devices, such as computer servers, gateways, network/routing devices (e.g., network routers), and data appliances (e.g., security appliances or other types of special purpose devices), and in various implementations, certain operations can be implemented in special purpose hardware, such as an ASIC or FPGA.
• devices such as computer servers, gateways, network/routing devices (e.g., network routers), and data appliances (e.g., security appliances or other types of special purpose devices), and in various implementations, certain operations can be implemented in special purpose hardware, such as an ASIC or FPGA.
• Firewalls typically deny or permit network transmission based on a set of rules. These sets of rules are often referred to as policies (e.g., network policies or network security policies). For example, a firewall can filter inbound traffic by applying a set of rules or policies to prevent unwanted outside traffic from reaching protected devices. A firewall can also filter outbound traffic by applying a set of rules or policies (e.g., allow, block, monitor, notify or log, and/or other actions can be specified in firewall rules or firewall policies, which can be triggered based on various criteria, such as are described herein). A firewall can also filter local network (e.g., intranet) traffic by similarly applying a set of rules or policies.
• policies e.g., network policies or network security policies.
• a firewall can filter inbound traffic by applying a set of rules or policies to prevent unwanted outside traffic from reaching protected devices.
• a firewall can also filter outbound traffic by applying a set of rules or policies (e.g., allow, block, monitor, notify or log, and/or other actions can be
• Security devices can include various security functions (e.g., firewall, anti-malware, intrusion prevention/detection, Data Foss Prevention (DFP), and/or other security functions), networking functions (e.g., routing, Quality of Service (QoS), workload balancing of network related resources, and/or other networking functions), and/or other functions.
• security functions e.g., firewall, anti-malware, intrusion prevention/detection, Data Foss Prevention (DFP), and/or other security functions
• networking functions e.g., routing, Quality of Service (QoS), workload balancing of network related resources, and/or other networking functions
• QoS Quality of Service
• routing functions can be based on source information (e.g., IP address and port), destination information (e.g., IP address and port), and protocol information.
• a basic packet filtering firewall filters network communication traffic by inspecting individual packets transmitted over a network (e.g., packet filtering firewalls or first generation firewalls, which are stateless packet filtering firewalls). Stateless packet filtering firewalls typically inspect the individual packets themselves and apply rules based on the inspected packets (e.g., using a combination of a packet’s source and destination address information, protocol information, and a port number).
• Application firewalls can also perform application layer filtering (e.g., application layer filtering firewalls or second generation firewalls, which work on the application level of the TCP/IP stack).
• Application layer filtering firewalls or application firewalls can generally identify certain applications and protocols (e.g., web browsing using HyperText Transfer Protocol (HTTP), a Domain Name System (DNS) request, a file transfer using File Transfer Protocol (FTP), and various other types of applications and other protocols, such as Telnet, DHCP, TCP, UDP, and TFTP (GSS)).
• HTTP HyperText Transfer Protocol
• DNS Domain Name System
• FTP File Transfer Protocol
• Telnet Telnet
• DHCP Dynamic Hossion Control Protocol
• TCP Transmission Control Protocol
• UDP User Datagram Protocol
• GSS TFTP
• application firewalls can block unauthorized protocols that attempt to communicate over a standard port (e.g., an unauthorized/out of policy protocol attempting to sneak through by using a nonstandard port for that protocol can generally be identified using application firewalls).
• Stateful firewalls can also perform state-based packet inspection in which each packet is examined within the context of a series of packets associated with that network transmission’s flow of packets.
• This firewall technique is generally referred to as a stateful packet inspection as it maintains records of all connections passing through the firewall and is able to determine whether a packet is the start of a new connection, a part of an existing connection, or is an invalid packet.
• the state of a connection can itself be one of the criteria that triggers a rule within a policy.
• Advanced or next generation firewalls can perform stateless and stateful packet filtering and application layer filtering as discussed above.
• Next generation firewalls can also perform additional firewall techniques. For example, certain newer firewalls sometimes referred to as advanced or next generation firewalls can also identify users and content (e.g., next generation firewalls). In particular, certain next generation firewalls are expanding the list of applications that these firewalls can automatically identify to thousands of applications. Examples of such next generation firewalls are commercially available from Palo Alto Networks, Inc. (e.g., Palo Alto Networks’ PA Series firewalls).
• Palo Alto Networks next generation firewalls enable enterprises to identify and control applications, users, and content— not just ports, IP addresses, and packets— using various identification technologies, such as the following: APP-ID for accurate application identification, User-ID for user identification (e.g., by user or user group), and Content-ID for real-time content scanning (e.g., controlling web surfing and limiting data and file transfers).
• APP-ID for accurate application identification
• User-ID for user identification (e.g., by user or user group)
• Content-ID for real-time content scanning (e.g., controlling web surfing and limiting data and file transfers).
• These identification technologies allow enterprises to securely enable application usage using business-relevant concepts, instead of following the traditional approach offered by traditional port-blocking firewalls.
• special purpose hardware for next generation firewalls (implemented, for example, as dedicated appliances) generally provide higher performance levels for application inspection than software executed on general purpose hardware (e.g., such as security appliances provided by Palo Alto Networks, Inc., which use dedicated, function specific processing that is tightly integrated with a single-pass software engine to maximize network throughput while minimizing latency).
• general purpose hardware e.g., such as security appliances provided by Palo Alto Networks, Inc., which use dedicated, function specific processing that is tightly integrated with a single-pass software engine to maximize network throughput while minimizing latency.
• next generation firewalls can also be implemented using virtualized firewalls.
• next generation firewalls are commercially available from Palo Alto Networks, Inc. (e.g., Palo Alto Networks’ VM Series firewalls, which support various commercial virtualized environments, including, for example, VMware® ESXiTM and NSXTM, Citrix® Netscaler SDXTM, KVM/OpenStack (Centos/RHEL, Ubuntu®), and Amazon Web Services (AWS)).
• virtualized firewalls can support similar or the exact same next-generation firewall and advanced threat prevention features available in physical form factor appliances, allowing enterprises to safely enable applications flowing into, and across their private, public, and hybrid cloud computing environments.
• Automation features such as VM monitoring, dynamic address groups, and a REST-based API allow enterprises to proactively monitor VM changes dynamically feeding that context into security policies, thereby eliminating the policy lag that may occur when VMs change.
• FIG 1 illustrates an example of an environment in which malicious applications (“malware”) are detected and prevented from causing harm.
• malware malicious applications
• security platform 122 can be variously shared and/or refined among various entities included in the environment shown in Figure 1.
• devices such as endpoint client devices 104-110 can be protected from such malware.
• An“application” is used throughout the Specification to collectively refer to programs, bundles of programs, manifests, packages, etc., irrespective of form/platform.
• An“application” (also referred to herein as a“sample”) can be a standalone file (e.g., a calculator application having the filename“calculator. apk” or“calculator.exe”) and can also be an independent component of another application (e.g., a mobile advertisement SDK or library embedded within the calculator app).
• Malware refers to an application that engages in behaviors, whether clandestinely or not (and whether illegal or not), of which a user does not approve/would not approve if fully informed.
• Examples of malware include Trojans, viruses, rootkits, spyware, hacking tools, keyloggers, etc.
• One example of malware is a desktop application that collects and reports to a remote server the end user’s location (but does not provide the user with location-based services, such as a mapping service).
• Another example of malware is a malicious Android Application Package .apk (APK) file that appears to an end user to be a free game, but stealthily sends SMS premium messages (e.g., costing $10 each), running up the end user’s phone bill.
• APIK Android Application Package .apk
• malware is an Apple iOS flashlight application that stealthily collects the user’s contacts and sends those contacts to a spammer.
• Other forms of malware can also be detected/thwarted using the techniques described herein (e.g., ransomware).
• ransomware e.g., ransomware
• n-grams/feature vectors/output accumulation variables are described herein as being generated for malicious applications, techniques described herein can also be used in various embodiments to generate profiles for other kinds of applications (e.g., adware profiles, goodware profiles, etc.).
• client devices 104-108 are a laptop computer, a desktop computer, and a tablet (respectively) present in an enterprise network 140.
• client device 110 is a laptop computer present outside of enterprise network 140.
• Data appliance 102 is configured to enforce policies regarding communications between client devices, such as client devices 104 and 106, and nodes outside of enterprise network 140 (e.g., reachable via external network 118). Examples of such policies include ones governing traffic shaping, quality of service, and routing of traffic. Other examples of policies include security policies such as ones requiring the scanning for threats in incoming (and/or outgoing) email attachments, website content, files exchanged through instant messaging programs, and/or other file transfers. In some embodiments, data appliance 102 is also configured to enforce policies with respect to traffic that stays within enterprise network 140.
• FIG. 2A An embodiment of a data appliance is shown in Figure 2A.
• the example shown is a representation of physical components that are included in data appliance 102, in various embodiments.
• data appliance 102 includes a high performance multi core Central Processing Unit (CPU) 202 and Random Access Memory (RAM) 204.
• Data appliance 102 also includes a storage 210 (such as one or more hard disks or solid state storage units).
• storage 210 such as one or more hard disks or solid state storage units.
• data appliance 102 stores (whether in RAM 204, storage 210, and/or other appropriate locations) information used in monitoring enterprise network 140 and implementing disclosed techniques.
• Data appliance 102 can also include one or more optional hardware accelerators.
• data appliance 102 can include a cryptographic engine 206 configured to perform encryption and decryption operations, and one or more Field Programmable Gate Arrays (FPGAs) 208 configured to perform matching, act as network processors, and/or perform other tasks.
• FPGAs Field Programmable Gate Arrays
• data appliance 102 can be a dedicated device or set of devices.
• the functionality provided by data appliance 102 can also be integrated into or executed as software on a general purpose computer, a computer server, a gateway, and/or a network/routing device.
• at least some services described as being provided by data appliance 102 are instead (or in addition) provided to a client device (e.g., client device 104 or client device 110) by software executing on the client device.
• data appliance 102 Whenever data appliance 102 is described as performing a task, a single component, a subset of components, or all components of data appliance 102 may cooperate to perform the task. Similarly, whenever a component of data appliance 102 is described as performing a task, a subcomponent may perform the task and/or the component may perform the task in conjunction with other components. In various embodiments, portions of data appliance 102 are provided by one or more third parties. Depending on factors such as the amount of computing resources available to data appliance 102, various logical components and/or features of data appliance 102 may be omitted and the techniques described herein adapted accordingly. Similarly, additional logical components/features can be included in embodiments of data appliance 102 as applicable.
• One example of a component included in data appliance 102 in various embodiments is an application identification engine which is configured to identify an application (e.g., using various application signatures for identifying applications based on packet flow analysis). For example, the application identification engine can determine what type of traffic a session involves, such as Web Browsing - Social Networking; Web Browsing - News; SSH; and so on.
• Figure 2B is a functional diagram of logical components of an embodiment of a data appliance.
• the example shown is a representation of logical components that can be included in data appliance 102 in various embodiments.
• various logical components of data appliance 102 are generally implementable in a variety of ways, including as a set of one or more scripts (e.g., written in Java, python, etc., as applicable).
• data appliance 102 comprises a firewall, and includes a management plane 232 and a data plane 234.
• the management plane is responsible for managing user interactions, such as by providing a user interface for configuring policies and viewing log data.
• the data plane is responsible for managing data, such as by performing packet processing and session handling.
• Network processor 236 is configured to receive packets from client devices, such as client device 108, and provide them to data plane 234 for processing. Whenever flow module 238 identifies packets as being part of a new session, it creates a new session flow. Subsequent packets will be identified as belonging to the session based on a flow lookup. If applicable, SSL decryption is applied by SSL decryption engine 240. Otherwise, processing by SSL decryption engine 240 is omitted. Decryption engine 240 can help data appliance 102 inspect and control SSL/TLS and SSH encrypted traffic, and thus help to stop threats that might otherwise remain hidden in encrypted traffic. Decryption engine 240 can also help prevent sensitive content from leaving enterprise network 140.
• Decryption can be controlled (e.g., enabled or disabled) selectively based on parameters such as: URL category, traffic source, traffic destination, user, user group, and port.
• decryption policies e.g., that specify which sessions to decrypt
• decryption profiles can be assigned to control various options for sessions controlled by the policy. For example, the use of specific cipher suites and encryption protocol versions can be required.
• Application identification (APP-ID) engine 242 is configured to determine what type of traffic a session involves. As one example, application identification engine 242 can recognize a GET request in received data and conclude that the session requires an HTTP decoder.
• the identified application can change, and such changes will be noted by data appliance 102.
• a user may initially browse to a corporate Wiki (classified based on the URL visited as“Web Browsing - Productivity”) and then subsequently browse to a social networking site (classified based on the URL visited as“Web Browsing - Social Networking”).
• a social networking site classified based on the URL visited as“Web Browsing - Social Networking”.
• Different types of protocols have corresponding decoders.
• the packets are sent, by threat engine 244, to an appropriate decoder configured to assemble packets (which may be received out of order) into the correct order, perform tokenization, and extract out information.
• Threat engine 244 also performs signature matching to determine what should happen to the packet.
• SSL encryption engine 246 can re encrypt decrypted data. Packets are forwarded using a forward module 248 for transmission (e.g., to a destination).
• policies 252 are received and stored in management plane 232.
• Policies can include one or more rules, which can be specified using domain and/or host/server names, and rules can apply one or more signatures or other matching criteria or heuristics, such as for security policy enforcement for subscriber/IP flows based on various extracted parameters/information from monitored session traffic flows.
• An interface (I/F) communicator 250 is provided for management communications (e.g., via (REST) APIs, messages, or network protocol communications or other communication mechanisms).
• malware 130 suppose a malicious individual (using system 120) has created malware 130.
• the malicious individual hopes that a client device, such as client device 104, will execute a copy of malware 130, compromising the client device, and, e.g., causing the client device to become a hot in a botnet.
• the compromised client device can then be instructed to perform tasks (e.g., cryptocurrency mining, or participating in denial of service attacks) and to report information to an external entity, such as command and control (C&C) server 150, as well as to receive instructions from C&C server 150, as applicable.
• C&C command and control
• data appliance 102 has intercepted an email sent (e.g., by system 120) to a user,“Alice,” who operates client device 104. A copy of malware 130 has been attached by system 120 to the message.
• data appliance 102 could intercept an attempted download by client device 104 of malware 130 (e.g., from a website).
• data appliance 102 determines whether a signature for the file (e.g., the email attachment or website download of malware 130) is present on data appliance 102.
• a signature if present, can indicate that a file is known to be safe (e.g., is whitelisted), and can also indicate that the file is known to be malicious (e.g., is blacklisted).
• data appliance 102 is configured to work in cooperation with security platform 122.
• security platform 122 can provide to data appliance 102 a set of signatures of known-malicious files (e.g., as part of a subscription). If a signature for malware 130 is included in the set (e.g., an MD5 hash of malware 130), data appliance 102 can prevent the transmission of malware 130 to client device 104 accordingly (e.g., by detecting that an MD5 hash of the email attachment sent to client device 104 matches the MD5 hash of malware 130).
• Security platform 122 can also provide to data appliance 102 a list of known malicious domains and/or IP addresses, allowing data appliance 102 to block traffic between enterprise network 140 and C&C server 150 (e.g., where C&C server 150 is known to be malicious).
• the list of malicious domains (and/or IP addresses) can also help data appliance 102 determine when one of its nodes has been compromised. For example, if client device 104 attempts to contact C&C server 150, such attempt is a strong indicator that client 104 has been compromised by malware (and remedial actions should be taken accordingly, such as quarantining client device 104 from communicating with other nodes within enterprise network 140).
• security platform 122 can also provide other types of information to data appliance 102 (e.g., as part of a subscription) such as a set of machine learning models usable by data appliance 102 to perform inline analysis of files.
• a variety of actions can be taken by data appliance 102 if no signature for an attachment is found, in various embodiments.
• data appliance 102 can failsafe, by blocking transmission of any attachments not whitelisted as benign (e.g., not matching signatures of known good files).
• whitelist e.g., not matching signatures of known good files.
• data appliance 102 can fail-danger, by allowing transmission of any attachments not blacklisted as malicious (e.g., not matching signatures of known bad files).
• a drawback of this approach is that newly created malware (previously unseen by platform 122) will not be prevented from causing harm.
• data appliance 102 can be configured to provide the file
• data appliance 102 can prevent the email (and attachment) from being delivered to Alice until a response is received from security platform 122. Assuming platform 122 takes approximately 15 minutes to thoroughly analyze a sample, this means that the incoming message to Alice will be delayed by 15 minutes. Since, in this example, the attachment is malicious, such a delay will not impact Alice negatively. In an alternate example, suppose someone has sent Alice a time sensitive message with a benign attachment for which a signature is also not present.
• an alternate approach is to perform at least some real-time analysis on the attachment on data appliance 102 (e.g., while awaiting a verdict from platform 122). If data appliance 102 can independently determine whether the attachment is malicious or benign, it can take an initial action (e.g., block or allow delivery to Alice), and can adjust/take additional actions once a verdict is received from security platform 122, as applicable.
• an initial action e.g., block or allow delivery to Alice
• Security platform 122 stores copies of received samples in storage 142 and analysis is commenced (or scheduled, as applicable).
• storage 142 is an Apache Hadoop Cluster (HDFS).
• HDFS Apache Hadoop Cluster
• Results of analysis (and additional information pertaining to the applications) are stored in database 146.
• data appliances can be configured to automatically block the file download based on the analysis result.
• a signature can be generated for the malware and distributed (e.g., to data appliances such as data appliances 102, 136, and 148) to automatically block future file transfer requests to download the file determined to be malicious.
• security platform 122 comprises one or more dedicated commercially available hardware servers (e.g., having multi-core processor(s), 32G+ of RAM, gigabit network interface adaptor(s), and hard drive(s)) running typical server-class operating systems (e.g., Linux).
• Security platform 122 can be implemented across a scalable infrastructure comprising multiple such servers, solid state drives, and/or other applicable high-performance hardware.
• Security platform 122 can comprise several distributed components, including components provided by one or more third parties. For example, portions or all of security platform 122 can be implemented using the Amazon Elastic Compute Cloud (EC2) and/or Amazon Simple Storage Service (S3).
• EC2 Amazon Elastic Compute Cloud
• S3 Amazon Simple Storage Service
• security platform 122 can optionally perform static/dynamic analysis in cooperation with one or more virtual machine (VM) servers, such as VM server 124.
• VM virtual machine
• An example of a virtual machine server is a physical machine comprising commercially available server-class hardware (e.g., a multi-core processor, 32+ Gigabytes of RAM, and one or more Gigabit network interface adapters) that runs commercially available virtualization software, such as VMware ESXi, Citrix XenServer, or Microsoft Hyper- V.
• the virtual machine server is omitted.
• a virtual machine server may be under the control of the same entity that administers security platform 122, but may also be provided by a third party.
• the virtual machine server can rely on EC2, with the remainder portions of security platform 122 provided by dedicated hardware owned by and under the control of the operator of security platform 122.
• VM server 124 is configured to provide one or more virtual machines 126-128 for emulating client devices.
• the virtual machines can execute a variety of operating systems and/or versions thereof. Observed behaviors resulting from executing applications in the virtual machines are logged and analyzed (e.g., for indications that the application is malicious). In some embodiments, log analysis is performed by the VM server (e.g., VM server 124). In other embodiments, analysis is performed at least in part by other components of security platform 122, such as a coordinator 144.
• VM server e.g., VM server 124
• analysis is performed at least in part by other components of security platform 122, such as a coordinator 144.
• security platform 122 makes available results of its analysis of samples via a list of signatures (and/or other identifiers) to data appliance 102 as part of a subscription.
• security platform 122 can periodically send a content package that identifies malware apps (e.g., daily, hourly, or some other interval, and/or based on an event configured by one or more policies).
• An example content package includes a listing of identified malware apps, with information such as a package name, a hash value for uniquely identifying the app, and a malware name (and/or malware family name) for each identified malware app.
• the subscription can cover the analysis of just those files intercepted by data appliance 102 and sent to security platform 122 by data appliance 102, and can also cover signatures of all malware known to security platform 122 (or subsets thereof, such as just mobile malware but not other forms of malware (e.g., PDF malware)).
• platform 122 can also make available other types of information, such as machine learning models that can help data appliance 102 detect malware (e.g., through techniques other than hash-based signature matching).
• security platform 122 is configured to provide security services to a variety of entities in addition to (or, as applicable, instead of) an operator of data appliance 102.
• entities having their own respective enterprise networks 114 and 116, and their own respective data appliances 136 and 148, can contract with the operator of security platform 122.
• Other types of entities can also make use of the services of security platform 122.
• ISP Internet Service Provider
• client device 110 can contract with security platform 122 to analyze applications which client device 110 attempts to download.
• the owner of client device 110 can install software on client device 110 that communicates with security platform 122 (e.g., to receive content packages from security platform 122, use the received content packages to check attachments in accordance with techniques described herein, and transmit applications to security platform 122 for analysis).
• security platform 122 e.g., to receive content packages from security platform 122, use the received content packages to check attachments in accordance with techniques described herein, and transmit applications to security platform 122 for analysis).
• Figure 3 illustrates an example of logical components that can be included in a system for analyzing samples.
• Analysis system 300 can be implemented using a single device.
• the functionality of analysis system 300 can be implemented in a malware analysis module 112 incorporated into data appliance 102.
• Analysis system 300 can also be implemented, collectively, across multiple distinct devices.
• the functionality of analysis system 300 can be provided by security platform 122.
• analysis system 300 makes use of lists, databases, or other collections of known safe content and/or known bad content (collectively shown in Figure 3 as collection 314).
• Collection 314 can be obtained in a variety of ways, including via a subscription service (e.g., provided by a third party) and/or as a result of other processing (e.g., performed by data appliance 102 and/or security platform 122).
• Examples of information included in collection 314 are: URLs, domain names, and/or IP addresses of known malicious servers; URLs, domain names, and/or IP addresses of known safe servers; URLs, domain names, and/or IP addresses of known command and control (C&C) domains; signatures, hashes, and/or other identifiers of known malicious applications; signatures, hashes, and/or other identifiers of known safe applications; signatures, hashes, and/or other identifiers of known malicious files (e.g., Android exploit files); signatures, hashes, and/or other identifiers of known safe libraries; and signatures, hashes, and/or other identifiers of known malicious libraries.
• URLs, domain names, and/or IP addresses of known malicious servers URLs, domain names, and/or IP addresses of known safe servers
• signatures, hashes, and/or other identifiers of known malicious applications signature
• a new sample is received for analysis (e.g., an existing signature associated with the sample is not present in analysis system 300), it is added to queue 302.
• application 130 is received by system 300 and added to queue 302.
• Coordinator 304 monitors queue 302, and as resources (e.g., a static analysis worker) become available, coordinator 304 fetches a sample from queue 302 for processing (e.g., fetches a copy of malware 130). In particular, coordinator 304 first provides the sample to static analysis engine 306 for static analysis.
• resources e.g., a static analysis worker
• static analysis engine 306 for static analysis.
• one or more static analysis engines are included within analysis system 300, where analysis system 300 is a single device.
• static analysis is performed by a separate static analysis server that includes a plurality of workers (i.e., a plurality of instances of static analysis engine 306).
• the static analysis engine obtains general information about the sample, and includes it (along with heuristic and other information, as applicable) in a static analysis report 308.
• the report can be created by the static analysis engine, or by coordinator 304 (or by another appropriate component) which can be configured to receive the information from static analysis engine 306.
• the collected information is stored in a database record for the sample (e.g., in database 316), instead of or in addition to a separate static analysis report 308 being created (i.e., portions of the database record form the report 308).
• the static analysis engine also forms a verdict with respect to the application (e.g.,“safe,”“suspicious,” or“malicious”).
• the verdict can be“malicious” if even one“malicious” static feature is present in the application (e.g., the application includes a hard link to a known malicious domain).
• points can be assigned to each of the features (e.g., based on severity if found; based on how reliable the feature is for predicting malice; etc.) and a verdict can be assigned by static analysis engine 306 (or coordinator 304, if applicable) based on the number of points associated with the static analysis results.
• coordinator 304 locates an available dynamic analysis engine 310 to perform dynamic analysis on the application.
• analysis system 300 can include one or more dynamic analysis engines directly.
• dynamic analysis is performed by a separate dynamic analysis server that includes a plurality of workers (i.e., a plurality of instances of dynamic analysis engine 310).
• results of static analysis are provided as input to dynamic analysis engine 310.
• the static report information can be used to help select/customize the virtual machine instance used by dynamic analysis engine 310 (e.g. , Microsoft Windows 7 SP 2 vs. Microsoft Windows 10 Enterprise, or iOS 11.0 vs. iOS 12.0).
• a single dynamic analysis engine can manage all of the instances, or multiple dynamic analysis engines can be used (e.g., with each managing its own virtual machine instance), as applicable.
• actions taken by the application including network activity
• static analysis of a sample is omitted or is performed by a separate entity, as applicable.
• traditional static and/or dynamic analysis may be performed on files by a first entity. Once it is determined (e.g., by the first entity) that a given file is malicious, the file can be provided to a second entity (e.g., the operator of security platform 122) specifically for additional analysis with respect to the malware’s use of network activity (e.g. , by a dynamic analysis engine 310).
• the environment used by analysis system 300 is instrumented/hooked such that behaviors observed while the application is executing are logged as they occur (e.g., using a customized kernel that supports hooking and logcat). Network traffic associated with the emulator is also captured (e.g., using pcap).
• the log/network data can be stored as a temporary file on analysis system 300, and can also be stored more permanently (e.g., using HDFS or another appropriate storage technology or combinations of technology, such as MongoDB).
• the dynamic analysis engine (or another appropriate component) can compare the connections made by the sample to lists of domains, IP addresses, etc. (314) and determine whether the sample has communicated (or attempted to communicate) with malicious entities.
• the dynamic analysis engine stores the results of its analysis in database 316 in the record associated with the application being tested (and/or includes the results in report 312 as applicable).
• the dynamic analysis engine also forms a verdict with respect to the application (e.g.,“safe,” “suspicious,” or“malicious”).
• the verdict can be“malicious” if even one “malicious” action is taken by the application (e.g., an attempt to contact a known malicious domain is made, or an attempt to exfiltrate sensitive information is observed).
• points can be assigned to actions taken (e.g., based on severity if found; based on how reliable the action is for predicting malice; etc.) and a verdict can be assigned by dynamic analysis engine 310 (or coordinator 304, if applicable) based on the number of points associated with the dynamic analysis results.
• a final verdict associated with the sample is made based on a combination of report 308 and report 312 (e.g., by coordinator 304).
• malware samples may be generated each month (e.g., by nefarious individuals such as the operator of system 120, whether by making subtle changes to existing malware or by authoring new malware). Accordingly, there will exist many malware samples for which security platform 122 (at least initially) has no signature. Further, even where security platform 122 has generated signatures for newly created malware, resource constraints prevent data appliances, such as data appliance 102, from having/using a list of all known signatures (e.g., as stored on platform 122) at any given time.
• malware such as malware 130
• data appliance 102 operates on a“first-time allow” principle.
• data appliance 102 does not have a signature for a sample (e.g., sample 130) and submits it to security platform 122 for analysis, it takes security platform 122 approximately five minutes to return a verdict (e.g.,“benign,” “malicious,”“unknown,” etc.).
• a verdict e.g.,“benign,” “malicious,”“unknown,” etc.
• data appliance 102 can use the verdict (e.g.,“malicious”) to block subsequent transmissions of malware 130 to network 140, can block communications between system 120 and network 140, etc.
• the verdict e.g.,“malicious”
• data appliance 102 can use the verdict (e.g.,“malicious”) to block subsequent transmissions of malware 130 to network 140, can block communications between system 120 and network 140, etc.
• the second copy (and any subsequent copies) of sample 130 will be held by system 120 pending a response from security platform 122.
• data appliance 102 includes a malware analysis module 112.
• malware analysis module 112 One task that malware analysis module 112 can perform is inline malware detection.
• machine learning techniques can be applied to perform efficient analysis ofthe file on data appliance 102 (e.g., in parallel with other processing performed on the file by data appliance 102) and an initial maliciousness verdict can be determined by data appliance 102 (e.g., while awaiting a verdict from security platform 122).
• a session is a network transfer of information, including the files that appliance 102 is to analyze in accordance with techniques described herein.
• a single appliance might have millions of concurrent sessions, and the memory available to persist during a given session is extremely limited.
• a first difficulty in performing inline analysis on a data appliance such as data appliance 102 is that, due to such memory constraints, data appliance 102 will typically not be able to process an entire file at once, but instead receive a sequence of packets which it needs to process, packet by packet.
• a machine learning approach used by data appliance 102 will accordingly need to accommodate packet streams in various embodiments.
• a second difficulty is that in some cases, data appliance 102 will be unable to determine where an end of a given file being processed occurs (e.g., the end of sample 130 in a stream).
• a machine learning approach used by data appliance 102 will accordingly need to be able to make a verdict about a given file potentially midstream (e.g., halfway through receipt/processing of sample 130 or otherwise prior to the actual file end) in various embodiments.
• security platform 122 provides a set of machine learning models to data appliance 102 for data appliance 102 to use in conjunction with inline malware detection.
• the models incorporate features (e.g., n-grams or other features) determined by security platform 122 as corresponding to malicious files.
• Two example types of such models include linear classification models and non-linear classification models.
• linear classification models that can be used by data appliance 102 include logistic regression and linear support vector machines.
• An example of a non-linear classification model that can be used by data appliance 102 includes a gradient boosting tree (e.g., extreme Gradient Boosting (XGBoost)).
• XGBoost extreme Gradient Boosting
• the non-linear model is more accurate (and is better able to detect obfuscated/disguised malware), but the linear model uses considerably fewer resources on appliance 102 (and is more suitable for efficiently analyzing JavaScript or similar files).
• which type of classification model is used for a given file being analyzed can be based on a filetype associated with the file (and determined, e.g., by a magic number).
• data appliance 102 includes a threat engine 244
• the threat engine incorporates both protocol decoding and threat signature matching during a respective decoder stage and pattern match stage. Results of the two stages are merged by a detector stage.
• data appliance 102 When data appliance 102 receives a packet, data appliance 102 performs a session match to determine to which session the packet belongs (allowing data appliance 102 to support concurrent sessions). Each session has a session state which implicates a particular protocol decoder (e.g., a web browsing decoder, an FTP decoder, or an SMTP decoder). When a file is transmitted as part of a session, the applicable protocol decoder can make use of an appropriate file-specific decoder (e.g., a PE file decoder, a JavaScript decoder, or a PDF decoder).
• a protocol decoder e.g., a web browsing decoder, an FTP decoder, or an SMTP decoder.
• decoder 402 walks the traffic bytestream, following the corresponding protocol and marking contexts.
• a context is an end-of-file context (e.g., encountering ⁇ /script> while processing a JavaScript file).
• Decoder 402 can mark the end- of-file context in the packet, which can then be used to trigger execution of the appropriate model using the file’s observed features.
• explicit protocol- level tags may not be present for decoder 402 to identify/mark context with.
• decoder 402 can use other information (e.g., file size as reported in a header) to determine when feature extraction of a file should end (e.g., the overlay section begins) and execution using an appropriate model should be commenced.
• other information e.g., file size as reported in a header
• Decoder 402 comprises two parts.
• the first part of decoder 402 is a virtual machine portion (404) which can be implemented as a state machine using a state machine language.
• the second part of decoder 402 is a set of tokens 406 (e.g., deterministic finite automaton (DFA) or regular expressions) for triggering state machine transitions and actions when matched in traffic.
• Threat engine 244 also includes a threat pattern matcher 408 (e.g., using regular expressions) that performs pattern matching (e.g., against threat patterns).
• threat pattern matcher 408 can be provided (e.g., by security platform 122) with a table of strings (whether exact strings or wildcard strings) to match against, and corresponding actions to take in the event a string match is found.
• Detector 410 processes outputs provided by decoder 402 and threat pattern matcher 408 to take various actions.
• N-Grams The data in a session can be broken into a sequence of n-grams - a series of byte strings. As an example, suppose a portion of hexadecimal data in a session is:
• threat engine 244 is configured to analyze files using 8-grams. Other n-grams can also be used, such as 7-grams or 4-grams. In the example string above,“1023ae42f6f28762” is an 8-gram, “23ae42f6f28762aa” is an 8-gram, etc.
• the total number of different 8-grams possible in a byte sequence is 2 64 (18,446,744,073,709,551,616).
• threat pattern matcher 408 parses the packets for matches against strings in a table (e.g., by performing regular expression and/or exact string matches).
• a list of matches e.g., with each instance of a match identified by a corresponding pattern ID
• Actions on those matches are taken in the order of the offset (e.g., from lower to higher).
• a set of one or more actions to take is specified (e.g., via an action table that maps actions to pattern IDs).
• the set of 8-grams provided by security platform 122 can be added (e.g., as exact string matches) as additions to the table of matches that threat pattern matcher 408 is already performing (e.g., heuristic matches looking for specific indicia of malware, such as where a JavaScript file accesses a password store, or a PE file calls the Local Security Authority Subsystem Service (LSASS) API).
• LASS Local Security Authority Subsystem Service
• One advantage of this approach is that, instead of performing multiple passes through the packet (e.g., first evaluating for heuristic matches, and then evaluating for 8-gram matches), the 8-grams can be searched for in parallel with other searches performed by threat pattern matcher 408.
• 8-gram matches are used by both linear and non-linear classification models in various embodiments.
• Example actions that can be specified for n-gram matches include incrementing a weighted counter (e.g., for a linear classifier) and saving the match in a feature vector (e.g., for a non-linear classifier). Which action is taken can be specified based on the filetype associated with the packet (which determines which type of model is used).
• a given filetype is specified within the file’s header (e.g., as a magic number appearing in the first seven bytes of the file itself).
• threat engine 244 can select an appropriate model corresponding to the specified file type (e.g., based on a table provided by security platform 122 that enumerates filetypes and corresponding models).
• the magic number or other filetype identifier may not be probative of which classification model should be used.
• JavaScript would have a filetype of“textfile.”
• decoder 402 can be used to perform deterministic finite state automaton (DFA) pattern matching and apply heuristics (e.g., identifying ⁇ script> and other indicators that the file is JavaScript).
• DFA deterministic finite state automaton
• the determined filetype and/or selected classification model are saved in the session state.
• the filetype associated with a session can be updated as the session progresses, as applicable. For example, in a stream of text, when a ⁇ script> tag is encountered, the JavaScript filetype can be assigned for the session. When a corresponding ⁇ /script> is encountered, the filetype can be changed (e.g., back to plaintext).
• C is the threshold for a verdict of maliciousness, meaning that if a summation for a given file is less than C, the file is assigned a verdict of benign, and if the summation is equal to or greater than C, the file is assigned a verdict of malicious.
• a single float (d) is used to track the score of the incoming file, and a hash table is used to store observed n-grams and corresponding coefficients (i.e., X j and [i j ).
• n-gram features e.g., as provided by security platform 122
• the single float (b ⁇ ) which matches that feature in the hash table is added (e.g., to d).
• C threshold value
• feature x is equal to the number of times the ith n-gram is observed.
• ith n-gram is observed for a particular file four times.
• 4 * b can be rewritten as b ⁇ + b ⁇ + b ⁇ + b.
• ⁇ instead of counting how many times (i.e., 4 times) the ith n- gram is observed and then multiplying by b ⁇ , an alternate approach is to add b, each time the ith n-gram is observed.
• 3 * b j can similarly be written as b j + b j + b j , each time adding P j instead of counting how many times b j was observed and then adding at the end.
• This approach allows a 4 byte float to be used as the entire per session memory, and is contrasted with an approach in which the per session memory is proportional to the number of features, where the entire feature vector is stored in memory so that it can be multiplied by the weight vector.
• 4K would be needed for storage (compared to the single 4 byte float), which is 1 ,000 times more expensive.
• non-linear classification approaches can be used in conjunction with the techniques described herein.
• One example of a non-linear classification model is a gradient boosting tree.
• a feature vector is initialized to all-zero vectors.
• the entire set of features for which presence is being detected e.g. , 1 ,000 features
• the entire set of features for which presence is being detected e.g. , 1 ,000 features
• the entire set of features for which presence is being detected e.g. , 1 ,000 features
• some efficiency can still be gained by down-sampling the features to be one byte (0-255) rather than a full 4 byte float (as might be used on a device that is not memory constrained).
• the non-linear classification model can be built using both n-gram (e.g., 8-gram) and non n-gram features.
• n-gram e.g., 8-gram
• non n-gram features is the purported size of the file (which can be read as a value out of a packet containing the file’s header).
• any file data appearing after the purported end of the file is referred to as an overlay.
• the purported file length can be used as a proxy for how long the file is expected to be.
• the non-linear classifier can be run against the file’s packet stream until the purported file length is reached, and then a verdict can be formed for the file irrespective of whether or not the end of file was in fact reached. That a given file includes an overlay is also an example of a feature that can be used as part of the non-linear classification model.
• the overlay portion of the file is not analyzed, again - analysis can be performed prior to the actual end of file.
• feature extraction occurs, and a maliciousness verdict is not formed until the actual end of file is reached.
• the tree model comprises 5,000 binary trees.
• Every node on each tree contains a feature and a corresponding threshold.
• An example of a portion of a tree is depicted in Figure 5.
• the left branch is taken (502).
• the right branch is taken (504).
• the tree is walked until a leaf node is reached (e.g., node 506), which has an associated value (e.g., 0.7).
• the values of each leaf reached (for each of the trees) are summed (rather than multiplied) to get a final score to calculate the verdict.
• the file can be considered benign, and if it is at or above the threshold, the file can be considered malicious.
• the lack of multiplication in obtaining the final score helps make use of the model more efficient in the resource constrained environment of data appliance 102.
• the trees themselves are fixed on data appliance 102
• the per session cost is the cost of storing the session’s feature vector, which can be zeroed out once analysis of the session is completed.
• FIG. 6 illustrates an example of a process for performing inline malware detection on a data appliance.
• process 600 is performed by data appliance 102, and in particular by threat engine 244.
• Threat engine 244 can be implemented using a script (or set of scripts) authored in an appropriate scripting language (e.g., Python).
• Process 600 can also be performed on an endpoint, such as client device 110 (e.g., by an endpoint protection application executing on client device 110).
• Process 600 begins at 602 when an indication is received by appliance 102 that a file is being transmitted as part of a session.
• an associated protocol decoder can call or otherwise make use of an appropriate file-specific decoder when the start of a file is detected by the protocol decoder.
• the filetype is determined (e.g., by decoder 402) and associated with the session (e.g., so that subsequent filetype analysis need not be performed until the filetype changes or the file packets cease being transmitted).
• n-gram analysis is performed on a sequence of received packets.
• the n-gram analysis can be performed inline with other analyses being performed on the session by appliance 102.
• appliance 102 can also determine whether any 8-grams in the packet match 8-grams provided by security platform 122.
• the corresponding pattern ID is used to map the condition to an action based on filetype. The action either increments a weighted counter (e.g., where the filetype is associated with a linear classifier) or updates a feature vector to account for the match (e.g., where the filetype is associated with a non-linear classifier).
• the n-gram analysis continues, packet by packet, until either an end-of-file condition or a checkpoint is reached.
• the appropriate model is used to determine a verdict for the file (i.e., comparing the final value obtained using the model against a maliciousness threshold).
• the models incorporate n-gram features and can also incorporate other features (e.g., in the case of the non-linear classifier).
• an action is taken in response to the determination made at 606.
• One example of a responsive action is terminating the session.
• Another example of a responsive action is allowing the session to continue, but preventing the file from being transmitted (and instead, being placed in a quarantine area).
• appliance 102 is configured to share its verdicts (whether benign verdicts, malicious verdicts, or both) with security platform 122.
• security platform 122 completes its independent analysis of the file, it can use the verdict reported by appliance 102 for a variety of purposes, including assessing the performance of the model that formed the verdict.
• FIG. 7B An example threat signature for a sample is shown in Figure 7B.
• the first value in each pair corresponds to the feature
• the second value corresponds to a count.
• the features comprising numbers e.g., feature“3905”
• the features comprising“J” and a number e.g., feature “J18”
• security platform 122 is configured to target a specific false positive rate (e.g., 0.001) when generating models for use by appliances such as data appliance 102. Accordingly, in some cases (e.g., one out of every one thousand files), data appliance 102 may incorrectly determine that a benign file is malicious when performing inline analysis using a model in accordance with techniques described herein. In such a scenario, if security platform 122 subsequently determines that the file is in fact benign, it can be added to a whitelist so that it is not subsequently flagged as being malicious (e.g., by another appliance).
• a specific false positive rate e.g., 0.001
• security platform 122 subsequently determines that the file is in fact benign, it can be added to a whitelist so that it is not subsequently flagged as being malicious (e.g., by another appliance).
• One approach to whitelisting is for security platform 122 to instruct appliance 102 to add the file to a whitelist stored at appliance 102.
• Another approach is for security platform 122 to instruct whitelist system 154 of false positives and for whitelist system 154 in turn to keep appliances such as appliance 102 up to date with false positive information.
• appliances such as appliance 102 is that they are resource constrained.
• One approach to minimizing resources used in maintaining a whitelist at an appliance is to maintain the whitelist using a Least Recently Used (LRU) cache.
• LRU Least Recently Used
• the whitelist can comprise file hashes, and can also be based on other elements, such as feature vectors or hashes of feature vectors.
• security platform 122 is configured to perform static and dynamic analysis on samples that it receives.
• Security platform 122 can receive samples for analysis from a variety of sources.
• sample source is a data appliance (e.g., data appliances 102, 136, and 148).
• Other sources e.g., one or more third party providers of samples, such as other security appliance vendors, security researchers, etc.
• security platform 122 can use the corpus of samples that it receives to build models (e.g., which can then be used by security appliance 102 in accordance with embodiments of the techniques described herein).
• static analysis engine 306 is configured to perform feature extraction on samples that it receives (e.g., while also performing other static analysis functions as described above).
• An example process for performing feature extraction e.g., by security platform 122 is depicted in Figure 8A.
• Process 800 begins at 802 when static analysis of a sample is commenced.
• feature extraction (804), all 8-grams (or other applicable n-grams in embodiments where 8-grams are not used) are extracted out of the sample being processed (e.g., sample 130 in Figure 3).
• a histogram of the 8- grams in the sample being analyzed is extracted (e.g., into a hash table), which indicates the number of times a given 8-gram was observed in the sample being processed.
• One benefit of extracting 8-grams during feature analysis by static analysis engine 306 is that potential privacy and contractual problems in using samples obtained from third parties (e.g., in constructing models) can be mitigated, as the original file cannot be reconstructed from the resulting histogram.
• the extracted histogram is stored at 806.
• static analysis engine 306 stores the extracted histogram (e.g., represented using a hash table) for a given sample in storage 142 (e.g., a Hadoop cluster) along with the histograms extracted from other samples.
• the data in Hadoop is compressed and when operations are performed on the Hadoop data, the needed data is uncompressed on the fly.
• An example hash table (represented in JSON) for a file is shown in Figure 7A.
• Line 702 indicates the SHA-256 hash of the file.
• Line 704 indicates the UNIX time at which sample 130 arrives at security platform 122.
• Line 706 indicates a count of n- grams in the overlay section (e.g.,‘d00fbf4e088bc366’: 1 represents that one instance of ‘d00fbf4e088bc366’ was found in the overlay section.
• Line 708 indicates a count of each of the 8-grams present in the file.
• Line 710 indicates that the file has an overlay.
• Line 712 indicates that the filetype of the file is“.exe.”
• Line 714 indicates the UNIX time at which security platform 122 finished processing sample 130.
• Line 716 indicates a count of each of the non 8-gram features the file hit.
• line 718 indicates that the file was determined (e.g., by security platform 122) to be malicious.
• the set of 8-gram histograms stored in the Hadoop cluster grows by approximately three terabytes of 8-gram histogram data per day.
• the histograms will correspond to both malicious and benign samples (which will be labeled as such, e.g., based on results of other static and dynamic analyses performed by security platform 122 as described above).
• a histogram of 8-grams extracted from a sample being analyzed will be approximately 10% larger than the file itself, and a typical sample will have a histogram comprising approximately 1 million different 8-grams.
• the total number of different possible 8-grams is 2 64 .
• the classification models sent by security platform 122 e.g., as part of a subscription
• devices such as data appliance 102
• the classification models sent by security platform 122 comprise only a few thousand features (e.g., 1,000 features).
• One example way to reduce the set of potentially up to 2 64 features to the most important 1,000 features for use in a model is to use a mutual information technique. Other approaches can also be used as applicable (e.g., Chi-squared score).
• the four needed parameters include the number of malicious samples having a given feature, the number of benign samples having the given features, the total number of malicious samples, and the total number of benign samples.
• One benefit of mutual information is that it can efficiently be used on very large data sets.
• the mutual information approach can be performed in a single pass (i.e., through all the 8-gram histograms stored in the Hadoop cluster dataset for a given filetype) by distributing the task across multiple mappers, each of which is responsible for handling a specific feature.
• Those features having the highest mutual information can be selected as the set of features most indicative of maliciousness and/or most indicative of benignness, as applicable.
• the resulting 1,000 features can then be used to build models (e.g., linear classification models and non-linear classification models) as applicable.
• model builder 152 (implemented using a set of open source tools and/or scripts authored in an appropriate language such as python) saves the top 1,000 features and applicable weights as the set of n-gram features for appliance 102 to check against (e.g., as described in Section V.A.4 above).
• the non-linear classification model is also built by model builder 152 using the top 1,000 (or other desired number) of features.
• the non-linear classification model is constructed predominantly using the top features (e.g., 950) but also incorporates other, non n-gram features (e.g., 50 such features) that can also be detected during packet-by-packet feature extraction and analysis.
• non n-gram features that can be incorporated into the non-linear classification model include: (1) the size of the header, (2) the presence or absence of a checksum in the file, (3) number of sections in the file, (4) the purported length of the file (as indicated in the header of the PE file), (5) whether the file includes an overlay portion, and (6) whether the file requires the Windows EFI Subsystem to execute the PE.
• a larger set of features is determined.
• the top 5,000 features can initially be selected using mutual information. That set of 5,000 can then be used as input to a traditional feature selection technique (e.g., bagging) which might not scale well to very large datasets (e.g., the entire Hadoop dataset), but be more effective on a reduced set (e.g., 5,000 features).
• the traditional feature selection technique can be used to select the final 1 ,000 features from the set of 5,000 features identified using mutual information.
• an example way to construct the non-linear model is to use an open source tool such as scikit-leam or XGBoost.
• an open source tool such as scikit-leam or XGBoost.
• parameter tuning can be performed, such as by using cross-validation.
• Process 850 is performed by security platform 122.
• Process 850 begins at 852 when a set of extracted features (e.g., including n-gram features) is received.
• a set of extracted features e.g., including n-gram features
• One example way the set of features can be received is by reading features stored as a result of process 800.
• a reduced set of features is determined from the features received at 852.
• an example way of determining a reduced set of features is by using mutual information. Other approaches (e.g., Chi-squared score) can also be used.
• Models e.g., generated by model builder 152 using process 850
• data appliance 102 and other applicable recipients e.g., data appliances 136 and 148.
• model builder 152 generates models (e.g., linear and non-linear classification models) on a daily (or other applicable) basis.
• security platform 122 can help ensure that the models used by appliances such as appliance 102 detect the most current types of malware threats (e.g., those most recently deployed by nefarious individuals).
• updated models can be transmitted to data appliances such as data appliance 102.
• data appliances such as data appliance 102.
• updates adjust weights assigned to features.
• Such updates can be readily deployed to and adopted by appliances (e.g., as real-time updates).
• Such updates adjust the features themselves.
• Such updates can be more complicated to deploy because they may require patches to components of the appliance, such as the decoder.
• One benefit of using overtraining during model generation is that the model can take into account whether the decoder is capable of detecting particular features or not.
• appliances are required (e.g., by security platform 122) to deploy updates to models as they are received.
• appliances are allowed to selectively deploy updates (at least for a period of time).
• the existing model and new model can both be run in parallel on appliance 102 for a period of time (e.g., with the existing model being used in production and the new model reporting on actions that it would take without actually taking them).
• An administrator of the appliance is able to indicate whether the existing model or the new model should be used to process traffic on the appliance (e.g., based on which model performs better).
• appliance 102 provides telemetry back to security platform 122 that indicates information such as which model(s) are running on appliance 102 and how effective the model(s) are (e.g., false positive statistical information).
• security platform 122 indicates information such as which model(s) are running on appliance 102 and how effective the model(s) are (e.g., false positive statistical information).

Landscapes

• Engineering & Computer Science (AREA)
• Computer Security & Cryptography (AREA)
• General Engineering & Computer Science (AREA)
• Computer Hardware Design (AREA)
• Computing Systems (AREA)
• Signal Processing (AREA)
• Computer Networks & Wireless Communication (AREA)
• Health & Medical Sciences (AREA)
• Virology (AREA)
• Theoretical Computer Science (AREA)
• Software Systems (AREA)
• General Health & Medical Sciences (AREA)
• General Physics & Mathematics (AREA)
• Physics & Mathematics (AREA)
• Artificial Intelligence (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Data Mining & Analysis (AREA)
• Evolutionary Computation (AREA)
• Medical Informatics (AREA)
• Mathematical Physics (AREA)
• Data Exchanges In Wide-Area Networks (AREA)
• Computer And Data Communications (AREA)

Priority Applications (5)

Applications Claiming Priority (4)

Publications (1)

Family

ID=74193725

Family Applications (1)

Country Status (5)

Families Citing this family (1)

Citations (5)

Family Cites Families (2)

• 2020
  • 2020-07-06 EP EP20843721.0A patent/EP3999985A4/en active Pending
  • 2020-07-06 WO PCT/US2020/040928 patent/WO2021015941A1/en unknown
  • 2020-07-06 JP JP2022502913A patent/JP7411775B2/ja active Active
  • 2020-07-06 KR KR1020227001606A patent/KR20220053549A/ko active IP Right Grant
  • 2020-07-06 CN CN202080051255.4A patent/CN114072798A/zh active Pending
• 2023
  • 2023-12-25 JP JP2023218442A patent/JP2024023875A/ja active Pending

Patent Citations (5)

Non-Patent Citations (1)

Also Published As

Similar Documents

Legal Events