WO2016140038A1 - 通信先悪性度算出装置、通信先悪性度算出方法及び通信先悪性度算出プログラム - Google Patents
通信先悪性度算出装置、通信先悪性度算出方法及び通信先悪性度算出プログラム Download PDFInfo
- Publication number
- WO2016140038A1 WO2016140038A1 PCT/JP2016/054102 JP2016054102W WO2016140038A1 WO 2016140038 A1 WO2016140038 A1 WO 2016140038A1 JP 2016054102 W JP2016054102 W JP 2016054102W WO 2016140038 A1 WO2016140038 A1 WO 2016140038A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- communication destination
- malignancy
- target
- destination
- calculating
- Prior art date
Links
Images
Classifications
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Definitions
- the present invention relates to a communication destination malignancy calculation apparatus, a communication destination malignancy calculation method, and a communication destination malignancy calculation program.
- Measures implemented on the terminal and those implemented on the network are used as cyber attack countermeasures.
- measures to be implemented on the terminal methods using anti-virus software, methods using host type IDS (Intrusion Detection System) and host type IPS (Intrusion Prevention System) are used. In these methods, software is installed in the terminal to implement countermeasures.
- IDS Intrusion Detection System
- IPS Intrusion Prevention System
- an inspection device is arranged on a communication path of a network.
- a technique for inspecting communication of a DNS query or a DNS response at a place where communication to a DNS server can be monitored in a communication path of a network has been proposed (see, for example, Non-Patent Document 1 or 2).
- SIEM Security Information and Event Management
- malware infection attacks and other cyber attacks are collected on a decoy system called a honeypot.
- malware is actually operated by a malware analysis system called a sandbox to collect malware communication destinations and communication contents, and communication destinations and communication contents determined to be attacks by spam mail countermeasure systems and DDoS countermeasure systems. Collect information on communications related to attacks.
- the IP address of the communication destination is blacklisted, and communication with the IP address as a partner is determined as an attack.
- the information to be blacklisted may be a uniform resource locator (URL: Uniform Resource Locator) or a domain name.
- URL Uniform Resource Locator
- the URL or domain name may be blacklisted with a regular expression. .
- the notation method of each item may differ depending on the device or software, but in recent years SIEM products As a result, a technique for converting log information shown in different notations into a unified notation method and tabulating the information is also widespread.
- malware when analyzing malware in the sandbox, the malware generates access to benign communication destinations and access to malicious communication destinations that change over time for the purpose of interfering with the analysis and confirming connection to the Internet.
- it is difficult to comprehensively and accurately identify and blacklist malignant communication destinations simply by collecting communication information related to cyber attacks.
- Non-Patent Document 1 or 2 proposes a method of blacklisting malicious communication destinations that have not been specified at that time using information collected up to a certain time. There is a problem that it is not possible to identify a malicious communication destination that is used in general and an malicious communication destination secured by an attacker for preparation for an attack.
- An object of the present invention is to automatically calculate the malignancy level of a communication destination without causing actual communication, and to accurately identify a malignant communication destination that cannot be identified only by referring to the latest blacklist.
- the communication destination malignancy calculation apparatus includes a target communication destination input unit that inputs a target communication destination that is a target for calculating malignancy, a communication destination that is known to be malignant, and a benign that is known to be benign.
- a feature extraction unit that extracts changes with time of presence / absence of publication as feature information of the known communication destination and the target communication destination, and the target communication destination based on the feature information of the known communication destination and the target communication destination
- a malignancy degree calculation unit for calculating the malignancy degree of.
- the communication destination malignancy calculation method of the present invention includes a target communication destination input step for inputting a target communication destination that is a target for calculating malignancy, a communication destination that is known to be malignant, and a benign that is known to be benign.
- a known communication destination input step for inputting a communication destination as a known communication destination, and the presence or absence of posting at a predetermined time in a list for communication destination evaluation of the known communication destination and the target communication destination,
- a malignancy level calculating step for calculating the malignancy level of.
- the communication destination malignancy calculation program of the present invention is benign to a target communication destination input step for inputting a target communication destination that is a target for calculating malignancy, a communication destination that is known to be malignant, and the like.
- a malignancy calculating step for calculating a malignancy of the target communication destination.
- the present invention it is possible to automatically calculate the malignancy level of a communication destination without causing actual communication, and to accurately identify a malignant communication destination that cannot be determined only by referring to the latest blacklist.
- FIG. 1 is a diagram illustrating an example of a configuration of a communication destination malignancy degree calculation system according to the first embodiment.
- FIG. 2 is a diagram illustrating an example of a target communication destination in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 3 is a diagram illustrating an example of a known communication destination in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 4 is a diagram illustrating an example of communication destination evaluation information in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 5 is a diagram illustrating an example of communication destination evaluation information in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 6 is a diagram illustrating an example of communication destination evaluation information in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 1 is a diagram illustrating an example of a configuration of a communication destination malignancy degree calculation system according to the first embodiment.
- FIG. 2 is a diagram illustrating an example of a target communication destination in the
- FIG. 7 is a diagram illustrating an example of a correspondence relationship of communication destinations in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 8 is a diagram illustrating an example of external information of an IP address in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 9 is a diagram illustrating an example of a method for extracting an IP address group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 10 is a diagram illustrating an example of a list of IP address groups related to domain names in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 11 is a diagram illustrating an example of feature information extracted from an IP address group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 12 is a diagram illustrating an example of external information of a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 13 is a diagram illustrating an example of a method for extracting a domain name group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 14 is a diagram illustrating an example of a list of domain name groups related to domain names in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 15 is a diagram illustrating an example of feature information extracted from a domain name group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 16 is a diagram illustrating an example of the malignancy calculated by the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 17 is a diagram illustrating an example of integrated feature information in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 18 is a diagram illustrating an example of the malignancy calculated by the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 19 is a diagram illustrating an example of processing of the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 20 is a diagram illustrating an example of processing performed by the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 21 is a diagram illustrating an example of a computer that functions as a communication destination malignancy calculation apparatus.
- FIG. 1 is a diagram illustrating an example of a configuration of a communication destination malignancy degree calculation system according to the first embodiment.
- the communication destination malignancy calculation system 10 includes a communication destination malignancy calculation device 100 and a communication destination information collection device 200.
- the communication destination malignancy calculation apparatus 100 includes a target communication destination input unit 101, a known communication destination input unit 102, a feature extraction unit 103, and a malignancy calculation unit 104.
- FIG. 2 is a diagram illustrating an example of a target communication destination in the communication destination malignancy calculation apparatus according to the first embodiment.
- the type of communication destination includes a domain name, URL, IP address, and the like.
- the line of serial number 1 in FIG. 2 indicates a communication destination whose domain name is “www.example.com”.
- the type of communication destination is not limited to that shown in the figure, and may be FQDN (Fully Qualified Domain Name) or the like.
- evaluation information and external information do not need to be included at this point as communication destination information input to the target communication destination input unit 101.
- FIG. 3 is a diagram illustrating an example of a known communication destination in the communication destination malignancy calculation apparatus according to the first embodiment.
- the data of the known communication destination first includes the type of communication destination and the communication destination as in the case of the target communication destination shown in FIG. Furthermore, information indicating malignancy or benign as shown in the label row of FIG. 3 is also required. For example, the line of serial number 1 in FIG. 3 indicates that the label of the communication destination whose domain name is “foo.example.com” is “benign”.
- the information shown in the label column is a malignant or benign binary value, but is not limited to that shown in FIG. 3, and may be a value indicating the degree of malignancy.
- the type of communication destination is not limited to that shown in the figure.
- the feature extraction unit 103 acquires presence / absence of a known communication destination and a target communication destination in a list for communication destination evaluation at a predetermined time point, and changes the presence / absence of the posting with the passage of time in the known communication destination and target. Extracted as feature information of the communication destination. In addition, the feature extraction unit 103 further acquires the external information of the known communication destination and the target communication destination and the correspondence relationship with the related communication destination, and calculates the statistics of the external information of the related communication destination group extracted from the correspondence relationship. Further extracted as feature information. Specific processing in the feature extraction unit 103 will be described later together with description of information collected by the communication destination information collection device 200.
- the feature extraction unit 103 may acquire the presence / absence of postings collected in a predetermined period at a predetermined cycle from a list for communication destination evaluation.
- the known communication destination and the target communication destination are domain names
- the related communication destinations are the known communication destination and the target communication destination, the top-level domain of the known communication destination and the target communication destination, and the known communication destination and the target communication destination.
- An IP address associated with a domain name possessed as a top level domain, or a domain name having a history associated with an IP address belonging to the same AS number as the known communication destination and the target communication destination may be used.
- the malignancy calculation unit 104 calculates the malignancy of the target communication destination based on the feature information of the known communication destination and the target communication destination.
- the malignancy calculation unit 104 is a model for calculating malignancy by supervised machine learning in which feature information of a known communication destination is input data and whether the known communication destination is malignant or benign is output data. And the malignancy of the target communication destination may be calculated using a model.
- the communication destination information collection device 200 includes an evaluation information collection unit 201, a correspondence relationship collection unit 202, and an external information collection unit 203. Information collected by each unit of the communication destination information collection device 200 is transferred to the feature extraction unit 103 of the communication destination malignancy calculation device 100.
- the evaluation information collection unit 201 collects communication destination evaluation information.
- the evaluation information collection unit 201 collects a predefined malignant communication destination list, benign communication destination list, and the like as communication destination evaluation information. Further, collection may be performed in accordance with a predetermined period and period set in advance. As a collection method, for example, the distribution destination of the collection target list is accessed using a known Web crawl technique.
- the list to be collected is not limited to a list indicating malignancy or benignity such as the above-described malignant communication destination list or benign communication destination list.
- any kind of evaluation such as a list of communication destinations with a large number of accesses, may be performed as long as the posting is started and ended periodically.
- FIG. 4 is a diagram illustrating an example of communication destination evaluation information in the communication destination malignancy calculation apparatus according to the first embodiment.
- the evaluation information collection unit 201 collects a plurality of malignant communication destination lists and benign communication destination lists, and uses the posting status of each list for a predetermined period as evaluation information.
- t, t ⁇ 1, and t ⁇ 2 indicate the current month, the previous month, and the previous month, respectively, and indicate whether or not they are listed in each list.
- the line of serial number 1 in FIG. 4 indicates that the communication destination “www.example.com” was listed in the “benign communication destination list 1” from the time t-2 to the time t.
- the line of serial number 2 is not listed in the “benign communication destination list 2” when the communication destination “www.example.com” is t-2, and “benign communication destination” at the time t-1 and t. It is shown in “List 2”.
- the evaluation information collection unit 201 may use, for example, all or part of the public blacklist as the malignant communication destination list.
- the evaluation information collection unit 201 uses all or a part of a popular domain list that is frequently viewed such as published on the Web as a benign communication destination list, or within an arbitrary network. It is possible to use a domain list that can be collected and viewed frequently.
- the evaluation information collection unit 201 is not limited to the case where each communication destination completely matches the communication destination described in the list. Even if a certain standard is satisfied, the communication destination may be regarded as being listed.
- the feature extraction unit 103 extracts feature information as shown in FIG. 5 or FIG. 6 based on, for example, the table of FIG. 5 and 6 are diagrams illustrating examples of communication destination evaluation information in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 5 shows the temporal changes in presence / absence of listing in each communication destination list as feature information.
- the communication destination “www.example.com” shown in the serial number 1 in FIG. 5 is stably listed in the benign communication destination list 1 at each time point in the range from t-2 to t.
- the unit 103 extracts feature information “stable posting”.
- the feature extraction unit 103 “publishing on the way” when posting is started in the middle, “end of posting on the way” when posting is finished on the way, and “no publication” when not posting at any point in time.
- Such feature information can be extracted.
- the feature information extraction method is not limited to that shown in FIG. 5.
- the feature information may be extracted based on a rule such that the feature information is a numerical value, and 1 is added to the numerical value when there is a publication.
- FIG. 6 is a combination of temporal changes in presence / absence of listing in a plurality of lists of communication destinations.
- the communication destination “www.example.com” indicated by serial number 1 in FIG. 6 is stably listed in the benign communication destination list 1 at each time point in the range from t-2 to t, and at the same time, benign communication Characteristic information “stable posting & halfway posting started” that the posting has been started in the middle of the previous list 2 is extracted.
- the feature information extraction method is not limited to that shown in FIG. 6.
- the feature information extraction method may be expressed by a sum or product of numerical values of temporal changes in presence / absence of publication.
- the correspondence collection unit 202 collects correspondences and histories of different types of communication destinations.
- the correspondence relationship collection unit 202 performs collection using, for example, a method called Passive DNS in which a DNS query is collected by a DNS server.
- Passive DNS a method called Passive DNS in which a DNS query is collected by a DNS server.
- the correspondence relationship collected by the correspondence relationship collection unit 202 and its history will be described with reference to FIG.
- FIG. 7 is a diagram illustrating an example of a correspondence relationship of communication destinations in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 7 shows an example of the correspondence between the domain name and the IP address and its history.
- the correspondence relationship between the domain name and the IP address can be obtained using, for example, a protocol represented by DNS.
- the correspondence between domain names and IP addresses may change over time depending on the operation and its form. Therefore, the correspondence collection unit 202 assigns a time stamp to the correspondence between the domain name and the IP address and collects it as a history.
- the line of serial number 1 in FIG. 7 indicates that the domain name “www.example.com” corresponds to the IP address “192.0.2.1” on January 1, 2015, 00:00:00. .
- the serial number 2 line corresponds to the domain name “www.example.com” and IP address “192.0.2.2” at 01:00:00 on January 1, 2015, one hour after the serial number 1 line. It shows that.
- the serial number 201 line is a domain name “example.com” on January 1, 2015, 00:00:00, and DNS round robin, which is a well-known load balancing technique, is used. 192.0.2.201,192.0.2.202 "indicates that it was compatible.
- the correspondence collection unit 202 When collecting the history of correspondence between domain names and IP addresses, the correspondence collection unit 202 is arranged in, for example, an authoritative DNS server that manages a top level domain or a second level domain, or an arbitrary in-house network A technique of observing DNS communication with a cache DNS server can be used.
- the external information collection unit 203 collects external information indicating the operation status and usage status of the communication destination. An example of the external information of the IP address collected by the external information collection unit 203 will be described with reference to FIG.
- FIG. 8 is a diagram illustrating an example of external information of an IP address in the communication destination malignancy calculation apparatus according to the first embodiment.
- the IP address external information includes the address prefix to which the IP address belongs, AS number, organization name, country, regional Internet registry (RIR), and the address assigned by the RIR. Assignment date etc. are mentioned.
- the external information for the IP address is not limited to that shown in FIG.
- the external information collection unit 203 also collects information uniquely collected using the WHOIS protocol, information published by each RIR, and information obtained through published services such as GeoIP (registered trademark) of MaxMind. External information for the IP address can be collected by using it.
- the address prefix which is the external information of the IP address “192.0.2.1” is “192.0.2.0/24”
- the AS number is “64501”
- the organization name is “TEST-NET-1”.
- the country is” US "
- the RIR is” ARIN "
- the address assignment date is" January 1, 2001 ".
- the feature extraction unit 103 uses the correspondence between the domain name and the IP address shown in FIG. 7 and the history thereof, and the feature information from the external information of the IP address shown in FIG. 8. An example in the case of extracting will be described.
- the feature extraction unit 103 extracts an IP address group related to the domain name by the method shown in FIG.
- FIG. 9 is a diagram illustrating an example of a method for extracting an IP address group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- the domain name 300 corresponds to the IP address “192.0.2.1” at t ⁇ 1, that is, January 1, 2015, 00:00:00, and t, that is, January 1, 2015, 01.
- the IP address “192.0.2.2” was supported.
- the domain name 350 which is the upper domain, corresponds to the IP addresses “192.0.2.201” and “192.0.2.202” at t ⁇ 1, that is, January 1, 2015, 00:00:00, and t, that is, 2015. It corresponds to the IP addresses “192.0.2.201” and “192.0.2.202” at 01:00:00 on January 1st.
- four IP addresses “192.0.2.1”, “192.0.2.2”, “192.0.2.201”, and “192.0.2.202” included in the IP address groups 301 and 351 are extracted as IP address groups related to the domain name 300.
- FIG. 10 is a diagram illustrating an example of a list of IP address groups related to domain names in the communication destination malignancy calculation apparatus according to the first embodiment.
- the IP addresses related to the domain name “www.example.com” indicated by the serial number 1 are “192.0.2.1”, “192.0.2.2”, “192.0.2.201”, and “192.0.2.202”. I understand.
- FIG. 11 is a diagram illustrating an example of feature information extracted from an IP address group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- the IP addresses related to the domain name “www.example.com” described in the row of serial number 1 in FIG. 11 are “192.0.2.1”, “192.0.2.2”, “192.0.2.201”, “192.0.2.202”.
- the feature extraction unit 103 refers to the number of address prefixes, the number of AS numbers, the number of organizations, the number of countries, the number of RIRs, the number of days allocated for addresses, which are statistics that can be calculated for these IP addresses with reference to FIG. Etc. are calculated as feature information. For example, in the row of serial number 1 in FIG.
- the related IP address calculated from the communication destination “www.example.com” is 4, the number of address prefixes is 1, the number of AS numbers is 1, the number of organization names is 1, the number of countries is 1 indicates that the number of RIRs is 1 and the number of days for address allocation is 1. Note that the statistics item is not limited to that shown in FIG.
- the feature extraction unit 103 extracts the feature information based on the external information of the related IP address group.
- As another method of extracting feature information by the feature extraction unit 103 there is a method of extracting feature information based on external information of related domain name groups.
- the feature extraction unit 103 may employ either a method of extracting feature information based on external information of an IP address group or a method of extracting feature information based on external information of a related domain name group. You can use both.
- FIG. 12 is a diagram illustrating an example of external information of a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- the domain name external information includes TLD (top level domain) to which the domain name belongs, WHOIS server name, NS server, domain name registration date, domain name update date, domain name expiration date, and the like. It is done.
- the external information for the domain name is not limited to that shown in FIG.
- the external information collection unit 203 can collect external information of domain names using information uniquely collected using the WHOIS protocol and information obtained by services published by third parties. .
- the TLD that is the external information of the domain name “www.example.com” is “.com”
- the WHOIS server name is “whois.example.com”
- the NS server is “ns1.
- the domain name registration date is “2001.1.1”
- the domain name update date is “2014.1.1”
- the domain name expiration date is “2015.1.1”.
- the feature extraction unit 103 extracts the feature information from the correspondence between the domain name and the IP address shown in FIG. 7 and its history, and the external information of the domain name shown in FIG. 12. An example of the case will be described.
- the feature extraction unit 103 extracts a domain name group related to the domain name by the method shown in FIG.
- FIG. 13 is a diagram illustrating an example of a method for extracting a domain name group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- a method for extracting a related domain name group of the domain name 400 will be described with reference to FIG.
- the domain name 400 corresponds to the IP address “192.0.2.1” at t ⁇ 1, that is, January 1, 2015, 00:00:00, and t, that is, January 1, 2015, 01.
- the IP address “192.0.2.2” was supported.
- a domain name that may correspond to an IP address group 450 including IP addresses “192.0.2.101” and “192.0.2.201” having the same AS number “64501” as “192.0.2.1” and “192.0.2.2” 410 and 420 are extracted as related domain name groups.
- FIG. 14 is a diagram illustrating an example of a list of domain name groups related to domain names in the communication destination malignancy calculation apparatus according to the first embodiment.
- the domain name group related to the domain name “www.example.com” indicated by the serial number 1 may be “www.example.com”, “foo.example.com”, and “example.com”. I understand.
- the domain name group related to a certain domain name includes the domain name itself.
- FIG. 15 is a diagram illustrating an example of feature information extracted from a domain name group related to a domain name in the communication destination malignancy calculation apparatus according to the first embodiment.
- the domain name group related to the domain name “www.example.com” described in the row of serial number 1 in FIG. 15 is “www.example.com”, “foo.example.com”, “example.com”.
- the feature extraction unit 103 calculates the number of related domain names, the number of TLDs, the number of WHOIS servers, the number of NS servers, and the like, which are statistics that can be calculated for these domain names with reference to FIG.
- the feature extraction unit 103 may calculate a domain name average, a domain name median, a domain name standard deviation, and the like as the statistic regarding the number of characters of the character string of the related domain name, and may use it as feature information. For example, in the row of serial number 1 in FIG.
- the statistics item is not limited to that shown in FIG.
- the malignancy calculation unit 104 calculates the malignancy for each communication destination as shown in FIG.
- FIG. 16 is a diagram illustrating an example of the malignancy calculated by the communication destination malignancy calculation apparatus according to the first embodiment.
- the malignancy calculation unit 104 calculates a malignancy of 0.3 for “www.example.com” that is one of the communication destinations for malignancy calculation shown in FIG. It shows that.
- the grade of malignancy is not only calculated as a continuous value, but when calculated as a discrete value, the grade of malignancy may be converted into an arbitrary value or label according to the result calculated as a continuous value or a discrete value. Yes, it is not limited to that shown in FIG.
- the malignancy calculation unit 104 applies a predetermined algorithm to the feature information of a known communication destination as shown in FIG. 3 to generate a training model that is a model for malignancy calculation.
- the characteristic information is based on the evaluation information as shown in FIGS. 5 and 6, and is based on the external information of the communication destination and the correspondence as shown in FIGS. included.
- the malignancy calculation unit 104 calculates the malignancy by using the generated training model and applying the algorithm when the training model is generated to the target communication destination.
- the training model is generated so that the known communication destinations with benign labels as shown in FIG. 3 have a low malignancy and the known communication destinations with a malignant label have a high malignancy.
- the malignancy of the communication destination “foo.example.com” in FIG. 3 is reduced and the malignancy of the communication destination “bar.example.com” is increased as a training model.
- the malignancy of the target communication destination can be obtained from the obtained regression equation.
- FIG. 17 is a diagram illustrating an example of integrated feature information in the communication destination malignancy calculation apparatus according to the first embodiment.
- FIG. 18 is a diagram illustrating an example of the malignancy calculated by the communication destination malignancy calculation apparatus according to the first embodiment.
- FIGS. 19 and 20 are diagrams illustrating an example of processing of the communication destination malignancy calculation apparatus according to the first embodiment. Specifically, FIG. 19 shows processing up to the above-described training model generation, and FIG. 20 shows processing for calculating a malignancy degree using the generated training model.
- a known malignant communication destination and a known benign communication destination are input to the known communication destination input unit 102 (step S101).
- the feature extraction unit 103 refers to whether or not the input known malignant communication destination and known benign communication destination are listed in the communication destination list (step S102). Then, the feature extraction unit 103 extracts, as feature information, a time change (step S103) of presence / absence in the communication destination list and a time change (step S104) of a combination of presence / absence in the communication destination list.
- the feature extraction unit 103 constructs history information on the correspondence between domain names and IP addresses (step S105). Then, external information indicating the usage status of the IP address is collected (step S106), and the feature extraction unit 103 builds the relationship of the IP address group related to the communication destination (step S107), and is related to the communication destination. The statistics of the IP address group are extracted as feature information (step S108).
- step S109 external information indicating the usage status of the domain name is collected (step S109), and the feature extraction unit 103 builds a relationship of domain names related to the communication destination (step S110), and relates to the communication destination.
- the statistic of the domain name group is extracted as feature information (step S111).
- the malignancy calculation unit 104 integrates the extracted feature information (step S112), applies a malignancy calculation algorithm (step S113), and outputs a training model (step S114).
- a communication destination and a training model for which malignancy is calculated are input to the target communication destination input unit 101 (step S201).
- the feature extraction unit 103 extracts, as feature information, a time change (step S202) of presence / absence in the communication destination list and a time change (step S203) of a combination of presence / absence in the communication destination list.
- the feature extraction unit 103 extracts the statistic of the IP address group related to the communication destination as feature information (step S204), and further extracts the statistic of the domain name group related to the communication destination as feature information (step S205). ).
- the malignancy calculation unit 104 integrates the extracted feature information (step S206), applies a malignancy calculation algorithm using the training model (step S207), and outputs the malignancy for the communication destination (step S207). S208).
- the communication destination malignancy calculation apparatus 100 inputs a target communication destination that is a target for calculating malignancy to the target communication destination input unit 101, and a communication destination that is known to be malignant and a communication that is known to be benign. Are input to the known communication destination input unit 102 as known communication destinations. Then, the feature extraction unit 103 changes the known communication destination and the target communication destination with the passage of time of the presence / absence of posting to the malignant communication destination list and the benign communication destination list at a predetermined time. Extracted as feature information. The malignancy calculation unit 104 calculates the malignancy of the target communication destination based on the feature information of the known communication destination and the target communication destination. For this reason, it is possible to accurately calculate a malignant communication destination that cannot be determined simply by referring to the latest blacklist by automatically calculating the malignancy of the communication destination without causing actual communication.
- the malignancy calculation unit 104 uses the feature information of the known communication destination as input data, and creates a model for malignancy calculation by supervised machine learning using the known communication destination as malignant or benign as output data. And the malignancy of the target communication destination is calculated using the generated model. For this reason, for example, it is possible to automatically calculate the malignancy level of the target communication destination with high accuracy simply by inputting the feature information of the target communication destination into a model that takes into account changes with time of the known communication destination. It is.
- communication destinations whose malignancy is unknown include communication destinations temporarily used by attackers and communication destinations that attackers are likely to use in the future. These refer to the blacklist. Alone could not determine whether it was malignant or not.
- a known malignant communication destination list and a benign communication destination list are obtained, and changes (for example, posting start and posting end) of each communication destination with the passage of time are analyzed.
- Information is extracted and compared with the feature information of the communication destination list to be analyzed, and the malignancy of each communication target is calculated, so actual communication is generated for communication destinations whose malignancy is unknown The degree of malignancy can be calculated without causing it.
- the feature extraction unit 103 can efficiently compare information of a plurality of lists by acquiring presence / absence of postings collected in a predetermined period at a predetermined period from a list for communication destination evaluation.
- the feature extraction unit 103 further acquires the history information of the correspondence relationship with the external information of the known communication destination and the target communication destination and the related communication destination, and the external information of the related communication destination group extracted from the history information. Statistics are further extracted as feature information.
- the related communication destination is the IP address associated with the top level domain of the communication destination, the domain name having the communication destination as the top level domain, or the domain name having the IP address belonging to the same AS number. is there.
- the malignancy of a wide range of communication destinations including not only target communication destinations and known communication destinations but also communication destinations related to them can be calculated, and more feature information can be obtained. Therefore, the calculation accuracy can be improved.
- each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated.
- the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or a part of the distribution / integration is functionally or physically distributed in arbitrary units according to various loads or usage conditions.
- all or any part of each processing function performed by each device is realized by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or hardware by wired logic.
- CPU Central Processing Unit
- program In addition, a program described in a language that can be executed by a computer can be created for the processing executed by the communication destination malignancy calculation apparatus described in the above embodiment. In this case, the same effect as the above-described embodiment can be obtained by the computer executing the program. Further, such a program may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read by the computer and executed to execute the same processing as in the above embodiment.
- An example of a computer that executes a program that implements the same function as that of the communication destination malignancy calculation apparatus shown in FIG. 1 will be described below.
- FIG. 21 is a diagram illustrating an example of a computer that functions as a communication destination malignancy calculation apparatus.
- the computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected by a bus 1080.
- the memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM (Random Access Memory) 1012 as illustrated in FIG.
- the ROM 1011 stores a boot program such as BIOS (Basic Input Output System).
- BIOS Basic Input Output System
- the hard disk drive interface 1030 is connected to the hard disk drive 1090 as illustrated in FIG.
- the disk drive interface 1040 is connected to the disk drive 1100 as illustrated in FIG.
- a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100.
- the serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120 as illustrated in FIG.
- the video adapter 1060 is connected to a display 1130, for example, as illustrated in FIG.
- the hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the above program is stored in, for example, the hard disk drive 1090 as a program module in which a command to be executed by the computer 1000 is described.
- various data described in the above embodiment is stored as program data in, for example, the memory 1010 or the hard disk drive 1090.
- the CPU 1020 reads the program module 1093 and the program data 1094 stored in the memory 1010 and the hard disk drive 1090 to the RAM 1012 as necessary, and executes them.
- the program module 1093 and the program data 1094 related to the program are not limited to being stored in the hard disk drive 1090, but may be stored in, for example, a removable storage medium and read out by the CPU 1020 via the disk drive 1100 or the like. Good.
- the program module 1093 and the program data 1094 related to the program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and via the network interface 1070. It may be read by the CPU 1020.
- LAN Local Area Network
- WAN Wide Area Network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
まず、図1を用いて、通信先悪性度算出システムの構成について説明する。図1は、実施形態1に係る通信先悪性度算出システムの構成の一例を示す図である。図1に示すように、通信先悪性度算出システム10は、通信先悪性度算出装置100及び通信先情報収集装置200を有する。
図19及び図20を用いて、通信先悪性度算出装置100の処理について説明する。図19及び図20は、実施形態1に係る通信先悪性度算出装置の処理の一例を示す図である。詳しくは、図19は、前述の訓練モデル生成までの処理を示しており、図20は生成された訓練モデルを利用して悪性度を算出する処理を示している。
通信先悪性度算出装置100は、悪性度を算出する対象である対象通信先を対象通信先入力部101へ入力し、悪性であることが既知の通信先と、良性であることが既知の通信先と、を既知通信先として既知通信先入力部102へ入力する。そして、特徴抽出部103は、既知通信先及び対象通信先の、悪性通信先リスト及び良性通信先リストへの所定の時点における掲載の有無の時間経過に伴う変化を既知通信先及び対象通信先の特徴情報として抽出する。悪性度算出部104は、既知通信先及び対象通信先の特徴情報に基づいて対象通信先の悪性度を算出する。このため、実通信を発生させることなく自動的に通信先の悪性度を算出し、最新のブラックリストを参照するだけでは判別できない悪性通信先を精度よく特定することが可能である。
また、図示した各装置の各構成要素は機能概念的なものであり、必ずしも物理的に図示の如く構成されていることを要しない。すなわち、各装置の分散・統合の具体的形態は図示のものに限られず、その全部又は一部を、各種の負荷や使用状況等に応じて、任意の単位で機能的又は物理的に分散・統合して構成することができる。さらに、各装置にて行なわれる各処理機能は、その全部又は任意の一部が、CPU(Central Processing Unit)及び当該CPUにて解析実行されるプログラムにて実現され、あるいは、ワイヤードロジックによるハードウェアとして実現され得る。
また、上記実施形態において説明した通信先悪性度算出装置が実行する処理について、コンピュータが実行可能な言語で記述したプログラムを作成することもできる。この場合、コンピュータがプログラムを実行することにより、上記実施形態と同様の効果を得ることができる。さらに、かかるプログラムをコンピュータが読み取り可能な記録媒体に記録して、この記録媒体に記録されたプログラムをコンピュータに読み込ませて実行することにより上記実施形態と同様の処理を実現してもよい。以下に、図1に示した通信先悪性度算出装置と同様の機能を実現するプログラムを実行するコンピュータの一例を説明する。
100 通信先悪性度算出装置
101 対象通信先入力部
102 既知通信先入力部
103 特徴抽出部
104 悪性度算出部
200 通信先情報収集装置
201 評価情報収集部
202 対応関係収集部
203 外部情報収集部
Claims (8)
- 悪性度を算出する対象である対象通信先を入力する対象通信先入力部と、
悪性であることが既知の通信先と、良性であることが既知の通信先と、を既知通信先として入力する既知通信先入力部と、
前記既知通信先及び前記対象通信先の、通信先評価のためのリストへの所定の時点における掲載の有無を取得し、前記掲載の有無の時間経過に伴う変化を前記既知通信先及び前記対象通信先の特徴情報として抽出する特徴抽出部と、
前記既知通信先及び前記対象通信先の前記特徴情報に基づいて前記対象通信先の悪性度を算出する悪性度算出部と、
を有することを特徴とする通信先悪性度算出装置。 - 前記悪性度算出部は、前記既知通信先の特徴情報を入力データとし、前記既知通信先が悪性であるか良性であるかを出力データとする教師あり機械学習によって悪性度算出のためのモデルを生成し、前記モデルを用いて前記対象通信先の悪性度を算出することを特徴とする請求項1に記載の通信先悪性度算出装置。
- 前記特徴抽出部は、前記通信先評価のためのリストから所定の周期で所定の期間に収集された掲載の有無を取得することを特徴とする請求項1に記載の通信先悪性度算出装置。
- 前記特徴抽出部は、前記既知通信先及び前記対象通信先の外部情報及び関連する通信先との対応関係の履歴情報をさらに取得し、前記履歴情報から抽出される関連する通信先群の前記外部情報の統計量を前記特徴情報としてさらに抽出することを特徴とする請求項1に記載の通信先悪性度算出装置。
- 前記既知通信先及び前記対象通信先はドメイン名であり、
前記関連する通信先は、前記既知通信先及び前記対象通信先、及び前記既知通信先及び前記対象通信先のトップレベルドメイン、及び前記既知通信先及び前記対象通信先をトップレベルドメインとして持つドメイン名と対応付けられたIPアドレスであることを特徴とする請求項4に記載の通信先悪性度算出装置。 - 前記既知通信先及び前記対象通信先はドメイン名であり、
前記関連する通信先は、前記既知通信先及び前記対象通信先と同じAS番号に所属するIPアドレスに対応付けられた履歴を持つドメイン名であることを特徴とする請求項4に記載の通信先悪性度算出装置。 - 悪性度を算出する対象である対象通信先を入力する対象通信先入力工程と、
悪性であることが既知の通信先と、良性であることが既知の通信先と、を既知通信先として入力する既知通信先入力工程と、
前記既知通信先及び前記対象通信先の、通信先評価のためのリストへの所定の時点における掲載の有無を取得し、前記掲載の有無の時間経過に伴う変化を前記既知通信先及び前記対象通信先の特徴情報として抽出する特徴抽出工程と、
前記既知通信先及び前記対象通信先の前記特徴情報に基づいて前記対象通信先の悪性度を算出する悪性度算出工程と、
を含んだことを特徴とする通信先悪性度算出方法。 - コンピュータに、
悪性度を算出する対象である対象通信先を入力する対象通信先入力ステップと、
悪性であることが既知の通信先と、良性であることが既知の通信先と、を既知通信先として入力する既知通信先入力ステップと、
前記既知通信先及び前記対象通信先の、通信先評価のためのリストへの所定の時点における掲載の有無を取得し、前記掲載の有無の時間経過に伴う変化を前記既知通信先及び前記対象通信先の特徴情報として抽出する特徴抽出ステップと、
前記既知通信先及び前記対象通信先の前記特徴情報に基づいて前記対象通信先の悪性度を算出する悪性度算出ステップと、
を実行させることを特徴とする通信先悪性度算出プログラム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017503394A JP6196008B2 (ja) | 2015-03-05 | 2016-02-12 | 通信先悪性度算出装置、通信先悪性度算出方法及び通信先悪性度算出プログラム |
EP16758732.8A EP3252646B1 (en) | 2015-03-05 | 2016-02-12 | Device for calculating maliciousness of communication destination, method for calculating maliciousness of communication destination, and program for calculating maliciousness of communication destination |
US15/554,136 US10701085B2 (en) | 2015-03-05 | 2016-02-12 | Communication partner malignancy calculation device, communication partner malignancy calculation method, and communication partner malignancy calculation program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015-043940 | 2015-03-05 | ||
JP2015043940 | 2015-03-05 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016140038A1 true WO2016140038A1 (ja) | 2016-09-09 |
Family
ID=56849255
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/054102 WO2016140038A1 (ja) | 2015-03-05 | 2016-02-12 | 通信先悪性度算出装置、通信先悪性度算出方法及び通信先悪性度算出プログラム |
Country Status (4)
Country | Link |
---|---|
US (1) | US10701085B2 (ja) |
EP (1) | EP3252646B1 (ja) |
JP (1) | JP6196008B2 (ja) |
WO (1) | WO2016140038A1 (ja) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018163464A1 (ja) * | 2017-03-09 | 2018-09-13 | 日本電信電話株式会社 | 攻撃対策決定装置、攻撃対策決定方法及び攻撃対策決定プログラム |
WO2019142399A1 (ja) * | 2018-01-17 | 2019-07-25 | 日本電信電話株式会社 | 収集装置、収集方法及び収集プログラム |
WO2019225381A1 (ja) * | 2018-05-23 | 2019-11-28 | 日本電信電話株式会社 | 信頼度算出装置、信頼度算出方法及びプログラム |
WO2020070916A1 (ja) * | 2018-10-02 | 2020-04-09 | 日本電信電話株式会社 | 算出装置、算出方法及び算出プログラム |
WO2021024532A1 (ja) * | 2019-08-07 | 2021-02-11 | 株式会社日立製作所 | 計算機システム及び情報の共有方法 |
JP2021111802A (ja) * | 2020-01-06 | 2021-08-02 | 富士通株式会社 | 検知プログラム、検知方法および情報処理装置 |
KR20210117852A (ko) * | 2020-03-20 | 2021-09-29 | 엘아이지넥스원 주식회사 | 악성 도메인 탐지 장치 및 방법 |
JP2021185449A (ja) * | 2020-05-25 | 2021-12-09 | 富士フイルムビジネスイノベーション株式会社 | 情報処理装置及び情報処理プログラム |
JP2021189721A (ja) * | 2020-05-29 | 2021-12-13 | 富士フイルムビジネスイノベーション株式会社 | 情報処理装置及び情報処理プログラム |
US11503046B2 (en) | 2019-01-25 | 2022-11-15 | Fujitsu Limited | Cyber attack evaluation method and information processing apparatus |
JP7468298B2 (ja) | 2020-10-28 | 2024-04-16 | 富士通株式会社 | 情報処理プログラム、情報処理方法、および情報処理装置 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPWO2019181005A1 (ja) * | 2018-03-19 | 2021-03-11 | 日本電気株式会社 | 脅威分析システム、脅威分析方法および脅威分析プログラム |
JP7501642B2 (ja) | 2020-08-31 | 2024-06-18 | 日本電信電話株式会社 | 判定装置、判定方法、および、判定プログラム |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012175296A (ja) * | 2011-02-18 | 2012-09-10 | Nippon Telegr & Teleph Corp <Ntt> | 通信分類装置及び方法 |
US20140298460A1 (en) * | 2013-03-26 | 2014-10-02 | Microsoft Corporation | Malicious uniform resource locator detection |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004135868A (ja) * | 2002-10-17 | 2004-05-13 | Fuji Photo Film Co Ltd | 異常陰影候補検出処理システム |
US7272853B2 (en) * | 2003-06-04 | 2007-09-18 | Microsoft Corporation | Origination/destination features and lists for spam prevention |
US8191149B2 (en) * | 2006-11-13 | 2012-05-29 | Electronics And Telecommunications Research Institute | System and method for predicting cyber threat |
US8041710B2 (en) * | 2008-11-13 | 2011-10-18 | Microsoft Corporation | Automatic diagnosis of search relevance failures |
KR101122650B1 (ko) * | 2010-04-28 | 2012-03-09 | 한국전자통신연구원 | 정상 프로세스에 위장 삽입된 악성코드 탐지 장치, 시스템 및 방법 |
US8521667B2 (en) * | 2010-12-15 | 2013-08-27 | Microsoft Corporation | Detection and categorization of malicious URLs |
US8762298B1 (en) * | 2011-01-05 | 2014-06-24 | Narus, Inc. | Machine learning based botnet detection using real-time connectivity graph based traffic features |
US9455993B2 (en) * | 2013-03-13 | 2016-09-27 | Lookingglass Cyber Solutions, Inc. | Computer network attribute bilateral inheritance |
US9972041B2 (en) * | 2015-02-18 | 2018-05-15 | Go Daddy Operating Company, LLC | Earmarking a short list of favorite domain names or searches |
-
2016
- 2016-02-12 US US15/554,136 patent/US10701085B2/en active Active
- 2016-02-12 EP EP16758732.8A patent/EP3252646B1/en active Active
- 2016-02-12 WO PCT/JP2016/054102 patent/WO2016140038A1/ja active Application Filing
- 2016-02-12 JP JP2017503394A patent/JP6196008B2/ja active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012175296A (ja) * | 2011-02-18 | 2012-09-10 | Nippon Telegr & Teleph Corp <Ntt> | 通信分類装置及び方法 |
US20140298460A1 (en) * | 2013-03-26 | 2014-10-02 | Microsoft Corporation | Malicious uniform resource locator detection |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPWO2018163464A1 (ja) * | 2017-03-09 | 2019-07-04 | 日本電信電話株式会社 | 攻撃対策決定装置、攻撃対策決定方法及び攻撃対策決定プログラム |
US11652845B2 (en) | 2017-03-09 | 2023-05-16 | Nippon Telegraph And Telephone Corporation | Attack countermeasure determination apparatus, attack countermeasure determination method, and attack countermeasure determination program |
WO2018163464A1 (ja) * | 2017-03-09 | 2018-09-13 | 日本電信電話株式会社 | 攻撃対策決定装置、攻撃対策決定方法及び攻撃対策決定プログラム |
JPWO2019142399A1 (ja) * | 2018-01-17 | 2020-04-30 | 日本電信電話株式会社 | 収集装置、収集方法及び収集プログラム |
WO2019142399A1 (ja) * | 2018-01-17 | 2019-07-25 | 日本電信電話株式会社 | 収集装置、収集方法及び収集プログラム |
US11556819B2 (en) | 2018-01-17 | 2023-01-17 | Nippon Telegraph And Telephone Corporation | Collection apparatus, collection method, and collection program |
WO2019225381A1 (ja) * | 2018-05-23 | 2019-11-28 | 日本電信電話株式会社 | 信頼度算出装置、信頼度算出方法及びプログラム |
JP2019204264A (ja) * | 2018-05-23 | 2019-11-28 | 日本電信電話株式会社 | 信頼度算出装置、信頼度算出方法及びプログラム |
WO2020070916A1 (ja) * | 2018-10-02 | 2020-04-09 | 日本電信電話株式会社 | 算出装置、算出方法及び算出プログラム |
JPWO2020070916A1 (ja) * | 2018-10-02 | 2021-04-30 | 日本電信電話株式会社 | 算出装置、算出方法及び算出プログラム |
US11928208B2 (en) | 2018-10-02 | 2024-03-12 | Nippon Telegraph And Telephone Corporation | Calculation device, calculation method, and calculation program |
JP7006805B2 (ja) | 2018-10-02 | 2022-01-24 | 日本電信電話株式会社 | 算出装置、算出方法及び算出プログラム |
US11503046B2 (en) | 2019-01-25 | 2022-11-15 | Fujitsu Limited | Cyber attack evaluation method and information processing apparatus |
JP2021026597A (ja) * | 2019-08-07 | 2021-02-22 | 株式会社日立製作所 | 計算機システム及び情報の共有方法 |
JP7297249B2 (ja) | 2019-08-07 | 2023-06-26 | 株式会社日立製作所 | 計算機システム及び情報の共有方法 |
WO2021024532A1 (ja) * | 2019-08-07 | 2021-02-11 | 株式会社日立製作所 | 計算機システム及び情報の共有方法 |
JP2021111802A (ja) * | 2020-01-06 | 2021-08-02 | 富士通株式会社 | 検知プログラム、検知方法および情報処理装置 |
KR102361513B1 (ko) * | 2020-03-20 | 2022-02-10 | 엘아이지넥스원 주식회사 | 악성 도메인 탐지 장치 및 방법 |
KR20210117852A (ko) * | 2020-03-20 | 2021-09-29 | 엘아이지넥스원 주식회사 | 악성 도메인 탐지 장치 및 방법 |
JP2021185449A (ja) * | 2020-05-25 | 2021-12-09 | 富士フイルムビジネスイノベーション株式会社 | 情報処理装置及び情報処理プログラム |
JP7413924B2 (ja) | 2020-05-25 | 2024-01-16 | 富士フイルムビジネスイノベーション株式会社 | 情報処理装置及び情報処理プログラム |
JP2021189721A (ja) * | 2020-05-29 | 2021-12-13 | 富士フイルムビジネスイノベーション株式会社 | 情報処理装置及び情報処理プログラム |
JP7468298B2 (ja) | 2020-10-28 | 2024-04-16 | 富士通株式会社 | 情報処理プログラム、情報処理方法、および情報処理装置 |
Also Published As
Publication number | Publication date |
---|---|
EP3252646A4 (en) | 2018-09-26 |
US20180270254A1 (en) | 2018-09-20 |
EP3252646B1 (en) | 2019-06-05 |
US10701085B2 (en) | 2020-06-30 |
EP3252646A1 (en) | 2017-12-06 |
JPWO2016140038A1 (ja) | 2017-07-27 |
JP6196008B2 (ja) | 2017-09-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6196008B2 (ja) | 通信先悪性度算出装置、通信先悪性度算出方法及び通信先悪性度算出プログラム | |
Singh et al. | Issues and challenges in DNS based botnet detection: A survey | |
US10237283B2 (en) | Malware domain detection using passive DNS | |
US10740363B2 (en) | Domain classification based on domain name system (DNS) traffic | |
Kührer et al. | Going wild: Large-scale classification of open DNS resolvers | |
Passerini et al. | Fluxor: Detecting and monitoring fast-flux service networks | |
US8745737B2 (en) | Systems and methods for detecting similarities in network traffic | |
US11652845B2 (en) | Attack countermeasure determination apparatus, attack countermeasure determination method, and attack countermeasure determination program | |
JP6315640B2 (ja) | 通信先対応関係収集装置、通信先対応関係収集方法及び通信先対応関係収集プログラム | |
Korczynski et al. | Reputation metrics design to improve intermediary incentives for security of TLDs | |
US20240259427A1 (en) | Domain squatting detection | |
US10432646B2 (en) | Protection against malicious attacks | |
Leita et al. | HARMUR: Storing and analyzing historic data on malicious domains | |
US20240039890A1 (en) | Detecting shadowed domains | |
Marchal | DNS and semantic analysis for phishing detection | |
Han et al. | A real-time android malware detection system based on network traffic analysis | |
Lee et al. | DGA-based malware detection using DNS traffic analysis | |
Wickramasinghe et al. | Uncovering ip address hosting types behind malicious websites | |
Dube et al. | An analysis of the use of DNS for malicious payload distribution | |
US20240179164A1 (en) | Strategically aged domain detection | |
Chen et al. | An improvement for fast-flux service networks detection based on data mining techniques | |
van Zyl | A longitudinal study of DNS traffic: Understanding current DNS practice and abuse | |
Müller | SIDekICk-Detecting Malicious Domain Names in the. nl Zone | |
Pa et al. | Finding malicious authoritative DNS servers |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16758732 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017503394 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15554136 Country of ref document: US |
|
REEP | Request for entry into the european phase |
Ref document number: 2016758732 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |