WO2018121675A1 - 一种车辆攻击检测方法和装置 - Google Patents

一种车辆攻击检测方法和装置 Download PDF

Info

Publication number
WO2018121675A1
WO2018121675A1 PCT/CN2017/119413 CN2017119413W WO2018121675A1 WO 2018121675 A1 WO2018121675 A1 WO 2018121675A1 CN 2017119413 W CN2017119413 W CN 2017119413W WO 2018121675 A1 WO2018121675 A1 WO 2018121675A1
Authority
WO
WIPO (PCT)
Prior art keywords
parameter value
vehicle body
state parameter
state
vehicle
Prior art date
Application number
PCT/CN2017/119413
Other languages
English (en)
French (fr)
Inventor
曹明革
刘健皓
Original Assignee
北京奇虎科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京奇虎科技有限公司 filed Critical 北京奇虎科技有限公司
Publication of WO2018121675A1 publication Critical patent/WO2018121675A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/71Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/70Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer
    • G06F21/82Protecting input, output or interconnection devices
    • G06F21/85Protecting input, output or interconnection devices interconnection devices, e.g. bus-connected or in-line devices

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a vehicle attack detection method and apparatus.
  • vehicles can pass 3G (3rd-Generation, 3rd Generation mobile communication technology) / 4G (the 4th Generation mobile communication technology), Wi-Fi (WIreless-Fidelity, Wireless fidelity and other methods to access the Internet, download video, music and other resources from the Internet, or remote control of the vehicle through the Internet, bringing great convenience to users.
  • 3G 3rd-Generation, 3rd Generation mobile communication technology
  • 4G the 4th Generation mobile communication technology
  • Wi-Fi WIreless-Fidelity
  • Wireless fidelity Wireless fidelity
  • the present application has been made in order to provide a vehicle attack detecting method and apparatus that overcomes the above problems or at least partially solves the above problems.
  • a vehicle attack detection method including:
  • a vehicle attack detecting apparatus including:
  • a data acquisition module for collecting body bus data
  • An information entropy determining module configured to determine an information entropy corresponding to the body bus data
  • the first attack determining module is configured to determine that the body bus is attacked and issue an alarm message if the information entropy exceeds a preset range.
  • a computer program comprising computer readable code, when the computer readable code is run on a terminal device, causing the terminal device to perform any of the aforementioned vehicle attack detection methods .
  • a computer readable medium storing a computer program such as the aforementioned vehicle attack detecting method.
  • a vehicle attack detection method and apparatus determines whether an body bus is attacked by detecting information entropy of body bus data. Since the information entropy of the body bus data can reflect the steady state of the body bus data, if the information entropy exceeds the preset range, the body bus data is in an unstable state, that is, an abnormality for the attack may occur in the body bus data. Data, therefore, it can be determined that the body bus is attacked and sends an alarm message, so that the user can take measures as soon as possible to stop the in-depth development of the attack, thereby improving the user's driving safety and information security.
  • FIG. 1 is a flow chart showing the steps of a vehicle attack detection method according to an embodiment of the present application
  • FIG. 2 is a flow chart showing the steps of a vehicle attack detection method according to an embodiment of the present application
  • FIG. 3 is a block diagram showing the structure of a vehicle attack detecting apparatus according to an embodiment of the present application
  • Fig. 4 schematically shows a block diagram of a terminal device for performing the method according to the present application
  • Fig. 5 schematically shows a storage unit for holding or carrying program code implementing the method according to the present application.
  • FIG. 1 a flow chart of steps of a vehicle attack detection method according to an embodiment of the present application is shown, which may specifically include the following steps:
  • Step 101 Collect body bus data
  • Step 102 Determine an information entropy corresponding to the body bus data.
  • Step 103 If the information entropy exceeds a preset range, determine that the body bus is attacked and issue an alarm message.
  • the attacker usually tampers with the body bus data to achieve the purpose of attacking the vehicle.
  • the embodiment of the present application can be used for performing security detection on a vehicle bus, discovering an attack behavior on a vehicle bus, and issuing an alarm message, thereby improving user traffic safety and information security.
  • the embodiment of the present application may preset a security detection rule, and use the security detection rule to detect the real-time collected body bus data to determine whether the body bus is attacked.
  • the security detection rule may be placed locally on the vehicle.
  • the security detection rule may be set to a T-BOX (Telematics BOX), an OBD (On-Board Diagnostic, an on-board diagnostic system), or the like.
  • T-BOX Telematics BOX
  • OBD On-Board Diagnostic
  • the embodiment of the present application can eliminate the need for additional independent functional modules to save hardware costs.
  • the security detection rule may be placed in the cloud server, and the security detection rule is sent by the cloud server to the vehicle networking device of the vehicle.
  • the vehicle networking device performs security detection on the real-time collected body bus data through the security detection rule issued by the cloud server, and sends an alarm message when determining that the body bus is attacked.
  • the vehicle networking device can also upload the collected body bus data and the detection result to the cloud server, so that the cloud server can analyze the body bus data and the detection result uploaded by each vehicle networking device, so as to continuously perform the security detection rule. Optimize and update.
  • the information entropy of the body bus data generally fluctuates within a certain range during the running state of the vehicle body, that is, the body bus data is usually in a certain stable state. If the information entropy of the body bus data exceeds the normal fluctuation range, it can be considered that the body bus is likely to be attacked. Therefore, the security detection rule may specifically: monitor information entropy corresponding to the body bus data, and if the information entropy exceeds the preset range, determine that the body bus is attacked.
  • the preset range may be a fluctuation range of information entropy of the body bus data that is statistically obtained under the normal state of the body bus.
  • the step of determining the information entropy corresponding to the body bus data may specifically include:
  • Step S11 Obtain a data amount of a vehicle body state parameter value in the body bus data and a total data amount of the vehicle body bus data in a preset time period;
  • Step S12 Determine an information entropy corresponding to the vehicle body bus data according to a data amount of the vehicle body state parameter value and a total data amount of the vehicle body bus data.
  • the attacker Before attacking the body bus, the attacker usually first attempts to attack the vehicle. The corresponding attack attempt may include: sending a large number of trial commands. In an attempt to derive a bus control command for a vehicle, such as a brake command, a door open command, etc., and use the obtained bus control command to perform a vehicle attack. During the normal running of the vehicle, the total data volume of the body bus data is usually maintained within a certain stable range.
  • the embodiment of the present application obtains the data amount of the vehicle body state parameter value in the body bus data and the total data amount of the vehicle body bus data in the preset time period, and according to the data of the vehicle body state parameter value. And the total amount of data of the body bus data to determine an information entropy corresponding to the body bus data.
  • the information entropy may reflect the state of the body bus data in the preset time period, and the state may include a steady state or an unstable state.
  • the calculated information entropy of the body bus data may be If it is a large value and exceeds the preset range, it can be determined that the body bus is unstable due to the attack, so an alarm message can be issued.
  • the information entropy corresponding to the body bus data may be calculated by determining a ratio of a data amount of the vehicle body state parameter value to a total data amount of the body bus data, and calculating the ratio, And a product of the logarithm of the ratio (the value obtained by taking the logarithm), and the negative value of the obtained product is used as the information entropy corresponding to the body bus data.
  • the manner of calculating the information entropy corresponding to the body bus data is only used as an application example of the present application. In a specific application, the specific calculation manner of the information entropy is not limited in the embodiment of the present application.
  • the vehicle attack detection method of the embodiment of the present application determines whether the vehicle body bus is attacked by detecting the information entropy of the body bus data. Since the information entropy of the body bus data can reflect the steady state of the body bus data, if the information entropy exceeds the preset range, the body bus data is in an unstable state, that is, an abnormality for the attack may occur in the body bus data. Data, therefore, it can be determined that the body bus is attacked and sends an alarm message, so that the user can take measures as soon as possible to stop the in-depth development of the attack, thereby improving the user's driving safety and information security.
  • the security detection rule may further be: monitoring whether the value of the vehicle body state parameter in the body bus data is in an abnormal state, and if the vehicle body state parameter value is in an abnormal state, It is determined that the body bus is attacked and an alarm message is issued.
  • FIG. 2 a flow chart of steps of a vehicle attack detection method according to an embodiment of the present application is shown, which may specifically include the following steps:
  • Step 201 Collect body bus data
  • Step 202 Determine an information entropy corresponding to the body bus data.
  • Step 203 If the information entropy exceeds a preset range, determine that the body bus is attacked and issue an alarm message;
  • Step 204 Determine whether the value of the vehicle body state parameter in the body bus data is in an abnormal state
  • Step 205 If the vehicle body state parameter value is in an abnormal state, determine that the vehicle body bus is attacked and issue an alarm message.
  • step 202 - step 203 may be performed first, and then step 204 - step 205 may be performed; or step 204 - step 205 may be performed first, then step 202 - step 203 may be performed; or step 202 - step 203 and step 204 - may be performed in parallel.
  • Step 205 can be.
  • the ECUs Electronic Control Units
  • the vehicle body state parameter value includes at least the following parameter values: vehicle speed, speed, speed, gear, oil quantity, water temperature.
  • the embodiment of the present application may provide the following alternatives for determining whether the value of the vehicle body state parameter in the body bus data is in an abnormal state.
  • the solution can detect whether the vehicle is attacked at the initial stage of the attack, and issue an alarm message to reduce the user's loss as early as possible.
  • the step of determining whether the vehicle body state parameter value in the body bus data is in an abnormal state may include: comparing the vehicle body state parameter value with a normal parameter value, if the vehicle body state parameter value is If the difference of the normal parameter values exceeds a preset threshold, it is determined that the vehicle body state parameter value is in an abnormal state.
  • the current speed is significantly higher than the normal speed, or the current water temperature is significantly higher than the normal water temperature, etc., and it may be determined that the vehicle body state parameter value is in an abnormal state.
  • the obtained vehicle state parameter values are not strictly independent, but have a certain relationship with each other.
  • the range of speed is related to the speed and gear
  • the temperature of the water temperature is related to the speed, outside temperature and travel time. Therefore, the scheme 2 detects the body state parameter value of the associated relationship to determine whether the body bus is attacked, thereby further improving the accuracy of the attack detection.
  • the step of determining whether the value of the vehicle body state parameter in the body bus data is in an abnormal state may include:
  • Step S21 determining whether the vehicle body state parameter values having the associated relationship respectively meet the corresponding normal range
  • Step S22 If at least one of the vehicle body state parameter values having the associated relationship does not meet the corresponding normal range, determining that the vehicle body state parameter value is in an abnormal state.
  • the speed, speed and gear are usually associated.
  • the gear is in the X position and the vehicle speed is in the range of M0-N0km/s
  • the corresponding normal speed should be in the range of M1-N1 RPM. If the current speed is exceeded, The normal range of the M1-N1 RPM determines that the body state parameter value is in an abnormal state. Alternatively, if it is detected that the current vehicle speed exceeds the normal range of M0-N0KM/S, it may be determined that the vehicle body state parameter value is in an abnormal state.
  • the manner of determining whether the value of the vehicle body state parameter is in an abnormal state provided by the foregoing solution 1 and the second embodiment is only an optional embodiment of the present application. In practical applications, different judgment modes may be adopted according to actual conditions.
  • it is also possible to determine whether the value of the vehicle body state parameter is in an abnormal state by detecting whether the value of the vehicle body state parameter is in a stable state within a preset time; for example, if the amount of oil detected in a short time is high or low, In the steady state, it can be determined that the body state parameter value is in an abnormal state.
  • the vehicle body state parameter value is in an abnormal state by detecting whether an abnormal display value is displayed on the instrument panel. For example, if the vehicle does not ignite, the instrument panel displays a certain speed or speed, etc., it can be determined that the vehicle body state parameter value is in an abnormal state.
  • the solution can collect samples of vehicle body state parameter values of most users during normal driving, and the sample of the vehicle body state parameter values may include: a sample of a normal body state parameter value, that is, a positive sample, and an abnormal sample of the body state parameter value. That is, the inverse sample obtains the feature vector according to the relationship between the positive state sample and the back state sample parameter value, and uses the above feature vector to train the positive sample and the inverse sample, and trains the state detection model through machine learning.
  • the state detection model is used to determine whether the body state parameter value in the body bus data is in an abnormal state. Since the state detection model can be trained by collecting a large number of vehicle body state parameter value samples, the state detection model has the classification and recognition capability of the normal state or the abnormal state, so that the accuracy of the detection attack can be improved.
  • the step of determining whether the value of the vehicle body state parameter in the body bus data is in an abnormal state may include:
  • Step S31 input the vehicle body state parameter value into a state detection model; the state detection model is obtained by training according to the collected body state parameter value samples;
  • Step S32 If the output result of the state detection model is an abnormal state, determine that the vehicle body state parameter value is in an abnormal state.
  • the specific training manner of the state detection model is not limited in the embodiment of the present application.
  • the vehicle body state parameter values such as the vehicle speed, the rotational speed, the gear position, the steering angle, the water temperature, and the oil temperature may be collected as a sample of the vehicle body state parameter value, and the body state parameter value samples are normalized and processed.
  • the normalized data is trained by BP (Error Back Propagation) algorithm to obtain the optimal model parameters and obtain the state detection model.
  • BP Error Back Propagation
  • the state detection model may be set in the cloud server, and the step of inputting the vehicle body state parameter value into the state detection model may specifically include:
  • the vehicle state parameter value may be collected by using the vehicle networking device and uploaded to the cloud server, and the cloud server uses the vehicle body state parameter value collected by the vehicle networking device to establish a state detection model for detecting the safety state of the vehicle by using the big data.
  • the value of the vehicle body state parameter collected in real time during the running of the vehicle can be analyzed. Once the vehicle body state parameter value is found to be in an abnormal state, an alarm can be issued, so that the body bus can be detected in time and early measures can be taken to stop the in-depth development of the attack. Reduce user losses.
  • the cloud server may deliver the state detection model to the vehicle networking device of the vehicle such that the state detection model can be used locally to detect whether the body bus data is attacked.
  • the vehicle networking device can also send the real-time collected vehicle state parameter values and the detection results to the cloud server, so that the cloud server can continuously optimize the state detection model.
  • the method may further include the following steps. :
  • Step S41 collecting driving behavior data of the user
  • Step S42 Adjust the state detection model according to the driving behavior data of the user to obtain a state detection model that conforms to the driving habits of the user.
  • the embodiment of the present application can adjust the training samples of the state detection model according to driving behavior data of different users to obtain a personalized state detection model that conforms to the driving habits of the user.
  • the number of rotation speeds, rapid acceleration, and rapid deceleration can reflect the user's driving intensity.
  • a slightly larger vehicle speed parameter such as vehicle speed and speed can be used as a positive sample, and the trained user's personalized state detection model can conform to the user's driving habits and can identify belongings.
  • the information entropy corresponding to the body bus data exceeds a preset range, or When the value of the vehicle body state parameter is in an abnormal state, the alarm information of the attack may be issued; however, if the physical detection means such as the repair shop detection determines that the body bus is not actually attacked, the attack detection result is incorrect. Other faults may occur in the vehicle, and a fault detection report can be generated at this time. And the body bus data, the body state parameter value and the fault detection result can be uploaded to the cloud server for big data analysis to further optimize the security detection rule and the state detection model, thereby reducing the probability of attack misjudgment and improving the attack detection. accuracy.
  • the embodiment of the present application can determine whether the body bus is attacked by detecting the information entropy of the body bus data, and can also determine whether the body bus is attacked by detecting whether the body state parameter value in the body bus data is in an abnormal state. . For example, by determining whether a single body state parameter value is in an abnormal state, it is possible to detect whether the vehicle is attacked at the initial stage of the attack, and to issue an alarm message to reduce the user's loss as early as possible. Alternatively, by detecting the value of the vehicle body state parameter having an associated relationship, it is determined whether the body bus is attacked, and the accuracy of the attack detection is further improved. Furthermore, it is also possible to detect whether the body bus is attacked by the state detection model, not only to improve the accuracy of the detection, but also to make the detection result conform to the driving habits of different users.
  • FIG. 3 a block diagram of a vehicle attack detecting apparatus according to an embodiment of the present application is shown, which may specifically include the following modules:
  • a data acquisition module 301 configured to collect body bus data
  • the first attack determining module 303 is configured to determine that the body bus is attacked and issue an alarm message if the information entropy exceeds a preset range.
  • the information entropy determining module 302 may specifically include:
  • a data quantity obtaining sub-module configured to acquire a data quantity of a vehicle body state parameter value and a total data volume of the vehicle body bus data in the body bus data in a preset time period;
  • the information entropy determining submodule is configured to determine an information entropy corresponding to the body bus data according to a data amount of the vehicle body state parameter value and a total data amount of the vehicle body bus data.
  • the apparatus may further include:
  • An abnormal state determining module configured to determine whether a body state parameter value in the body bus data is in an abnormal state
  • the second attack determining module is configured to determine that the vehicle body bus is attacked and issue an alarm message if the vehicle body state parameter value is in an abnormal state.
  • the abnormal state determining module may specifically include:
  • a first determining submodule configured to compare the body state parameter value with a normal parameter value, and if the difference between the body state parameter value and the normal parameter value exceeds a preset threshold, determining the body state parameter The value is in an abnormal state.
  • the abnormal state determining module may specifically include:
  • a second determining sub-module configured to determine whether the vehicle body state parameter values having the associated relationship respectively meet the corresponding normal range
  • the abnormality determining submodule is configured to determine that the vehicle body state parameter value is in an abnormal state if at least one of the vehicle body state parameter values having the associated relationship does not meet the corresponding normal range.
  • the abnormal state determining module may specifically include:
  • a model input submodule configured to input the vehicle body state parameter value into a state detection model; the state detection model is obtained by training according to the collected body state parameter value samples;
  • the result output submodule is configured to determine that the vehicle body state parameter value is in an abnormal state if an output result of the state detection model is an abnormal state.
  • the apparatus may further include:
  • a behavior collection module for collecting driving behavior data of the user
  • the model adjustment module is configured to adjust the state detection model according to the driving behavior data of the user to obtain a state detection model that conforms to a driving habit of the user.
  • the state detection model is set in a cloud server, and the model input sub-module may specifically include:
  • an uploading unit configured to upload the vehicle body state parameter value to the cloud server, to input the vehicle body state parameter value into a state detection model in the cloud server to perform abnormal state detection.
  • the vehicle body state parameter value includes at least the following parameters: vehicle speed, speed, speed, gear, oil amount, water temperature.
  • the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.
  • the various component embodiments of the present invention may be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components of the vehicle attack detection device in accordance with embodiments of the present invention.
  • the invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein.
  • a program implementing the invention may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
  • FIG. 4 shows a terminal device that can implement vehicle attack detection in accordance with the present invention.
  • the terminal device conventionally includes a processor 410 and a computer program product or computer readable medium in the form of a memory 420.
  • the memory 420 may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), an EPROM, a hard disk, or a ROM.
  • Memory 420 has a memory space 430 for program code 431 for performing any of the method steps described above.
  • storage space 430 for program code may include various program code 431 for implementing various steps in the above methods, respectively.
  • the program code can be read from or written to one or more computer program products.
  • These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks.
  • Such computer program products are typically portable or fixed storage units as described with reference to FIG.
  • the storage unit may have a storage section, a storage space, and the like arranged similarly to the storage 420 in the terminal device of FIG.
  • the program code can be compressed, for example, in an appropriate form.
  • the storage unit comprises computer readable code 431', ie code that can be read by a processor, such as 410, which, when executed by the terminal device, causes the terminal device to perform each of the methods described above step.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Alarm Systems (AREA)

Abstract

一种车辆攻击检测方法和装置,其中的方法具体包括:采集车身总线数据(101);确定所述车身总线数据对应的信息熵(102);若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息(103)。所述方法可以检测出车身总线是否受到攻击,在确定所述车身总线受到攻击时,可以发出告警信息,以使用户尽早采取措施制止攻击的深入发展,进而提高用户的行车安全以及信息安全。

Description

一种车辆攻击检测方法和装置 技术领域
本申请涉及通信技术领域,特别是涉及一种车辆攻击检测方法和装置。
背景技术
随着网络技术的不断发展,车辆可以通过3G(3rd-Generation,第三代移动通信技术)/4G(the 4th Generation mobile communication technology,第四代移动通信技术)、Wi-Fi(WIreless-Fidelity,无线保真)等方式接入互联网,从互联网中下载视频、音乐等资源,或者,还可以通过互联网对车辆实现远程控制,为用户带来极大的便利。
在互联网为用户带来便利的同时,车辆信息安全问题也变得尤为重要,越来越多的车辆局域网采用互联网标准,突破车辆内部的“防火墙”也就变得轻而易举,对于接入互联网的车辆,黑客经由外部网络就能够对行驶中的车辆发起攻击。造成车载设备和车载导航仪系统异常,或是泄露车内信息以及驾驶员个人隐私信息等,为用户驾驶以及用户信息带来极大的安全隐患。
然而,目前各大车辆厂商均缺乏对联网车辆攻击行为的主动检测以及防御能力。因此,亟需一种能够对黑客的攻击行为进行主动检测的安全机制,以提高用户的行车安全以及信息安全。
发明内容
鉴于上述问题,提出了本申请以便提供一种克服上述问题或者至少部分地解决上述问题的一种车辆攻击检测方法和装置。
依据本申请的一个方面,提供了一种车辆攻击检测方法,包括:
采集车身总线数据;
确定所述车身总线数据对应的信息熵;
若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息。
根据本申请的另一方面,提供了一种车辆攻击检测装置,包括:
数据采集模块,用于采集车身总线数据;
信息熵确定模块,用于确定所述车身总线数据对应的信息熵;
第一攻击确定模块,用于若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息。
根据本申请的另一方面,提供了一种计算机程序,包括计算机可读代码,当所述计算机可读代码在终端设备上运行时,导致所述终端设备执行前述任一个所述车辆攻击检测方法。
根据本申请的另一方面,提供了一种计算机可读介质,其中存储了如前述车辆攻击检测方法的计算机程序。
根据本申请实施例提供的一种车辆攻击检测方法和装置,通过检测车身总线数据的信息熵来判断车身总线是否受到攻击。由于车身总线数据的信息熵可以反映车身总线数据的稳定状态,如果该信息熵超出预置范围,则说明车身总线数据处于不稳地状态,也即车身总线数据中有可能出现用于攻击的异常数据,因此,可以确定所述车身总线受到攻击,并发出告警信息,以使用户尽早采取措施制止攻击的深入发展,进而提高用户的行车安全以及信息安全。
上述说明仅是本申请技术方案的概述,为了能够更清楚了解本申请的技术手段,而可依照说明书的内容予以实施,并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂,以下特举本申请的具体实施方式。
附图说明
通过阅读下文可选实施方式的详细描述,各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出可选实施方式的目的,而并不认为是对本申请的限制。而且在整个附图中,用相同的参考符号表示相同的部件。在附图中:
图1示出了根据本申请一个实施例的一种车辆攻击检测方法的步骤流程图;
图2示出了根据本申请一个实施例的一种车辆攻击检测方法的步骤流程 图;以及
图3示出了根据本申请一个实施例的一种车辆攻击检测装置的结构框图;
图4示意性地示出了用于执行根据本申请的方法的终端设备的框图;
图5示意性地示出了用于保持或者携带实现根据本申请的方法的程序代码的存储单元。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例,然而应当理解,可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反,提供这些实施例是为了能够更透彻地理解本公开,并且能够将本公开的范围完整的传达给本领域的技术人员。
参照图1,示出了根据本申请一个实施例的一种车辆攻击检测方法的步骤流程图,具体可以包括如下步骤:
步骤101、采集车身总线数据;
步骤102、确定所述车身总线数据对应的信息熵;
步骤103、若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息。
在实际应用中,攻击者通常通过对车身总线数据进行篡改,以达到攻击车辆的目的。本申请实施例可用于对车辆总线进行安全检测,以及时发现对车辆总线的攻击行为,并且发出告警信息,进而提高用户的行车安全以及信息安全。
在实际应用中,本申请实施例可以预先设置安全检测规则,并且利用所述安全检测规则对实时采集的车身总线数据进行检测,以判断车身总线是否受到攻击。可选地,所述安全检测规则可以置于车辆本地,例如,可以将所述安全检测规则设置于T-BOX(Telematics BOX,车载智能终端)、OBD(On-Board Diagnostic,车载诊断系统)等车联网设备中,由于所述车联网 设备具有采集车身总线数据的功能,因此,本申请实施例可以不用再额外增加独立的功能模块,以节省硬件成本。
或者,所述安全检测规则还可以置于云服务器中,由云服务器向车辆的车联网设备下发所述安全检测规则。所述车联网设备通过云服务器下发的安全检测规则对实时采集的车身总线数据进行安全检测,在确定车身总线受到攻击时,发出告警信息。所述车联网设备还可以将采集的车身总线数据以及检测结果上传至云服务器,以使云服务器可以对各车联网设备上传的车身总线数据以及检测结果进行分析,以不断对所述安全检测规则进行优化和更新。
本申请实施例中,车身总线数据的信息熵在车身运转状态过程中通常在一定范围内进行波动,也即车身总线数据通常处于某个稳定状态。如果车身总线数据的信息熵超出正常的波动范围,则可以认为车身总线有可能受到攻击。因此,所述安全检测规则具体可以为:监控车身总线数据对应的信息熵,若所述信息熵超出预置范围,则确定车身总线受到攻击。其中,所述预置范围可以为在车身总线正常状态下统计得到的车身总线数据信息熵的波动范围。
在本申请的一种可选实施例中,所述确定所述车身总线数据对应的信息熵的步骤,具体可以包括:
步骤S11、获取预设时间段内所述车身总线数据中车身状态参数值的数据量和所述车身总线数据的总数据量;
步骤S12、根据所述车身状态参数值的数据量和所述车身总线数据的总数据量,确定所述车身总线数据对应的信息熵。
在实际应用中,不同型号的车辆通常具有不同的总线控制命令,攻击者在对车身总线进行攻击前,通常首先对车辆进行攻击尝试,对应的攻击尝试过程可以包括:通过发送大量的尝试命令,以尝试得出某辆车辆的总线控制命令,如刹车命令、开门命令等,并利用得到的总线控制命令进行车辆攻击。在车辆正常行驶的过程中,车身总线数据的总数据量通常维持在某个稳定的范围内,如果在某段时间内,攻击者通过车身总线发送大量的刹车尝试命令, 则该段时间内车身总线数据中会出现大量的异常车身状态参数值,使得车身状态参数值的数据量显著增多,进而车身总线数据的总数据量也随之增加,从而导致车身总线数据的总数据量超出正常的波动范围。
也即在攻击者对车辆进行攻击尝试的过程中,攻击者会通过车身总线发送大量的尝试命令,使得车身总线数据中车身状态参数值的数据量和所述车身总线数据的总数据量发生明显的变化,因此,本申请实施例通过获取预设时间段内所述车身总线数据中车身状态参数值的数据量和所述车身总线数据的总数据量,并且根据所述车身状态参数值的数据量和所述车身总线数据的总数据量,确定所述车身总线数据对应的信息熵。该信息熵可以反映预设时间段内车身总线数据的状态,该状态可以包括稳定状态或者不稳定状态,例如,攻击者发送大量的尝试刹车的命令,则计算得到的车身总线数据的信息熵可能为一个较大的值,并且超出预置范围,则可以确定所述车身总线因受到攻击而不稳定,故可以发出告警信息。
在本申请实施例中,可以通过如下步骤计算所述车身总线数据对应的信息熵:确定所述车身状态参数值的数据量与所述车身总线数据的总数据量的比值,计算所述比值、以及所述比值的对数值(取对数得到的值)的乘积,将得到的乘积的负值作为所述车身总线数据对应的信息熵。
可以理解,上述计算车身总线数据对应的信息熵的方式仅作为本申请的一种应用示例,在具体应用中,本申请实施例对于所述信息熵的具体计算方式不加以限制。
综上,本申请实施例的车辆攻击检测方法,通过检测车身总线数据的信息熵来判断车身总线是否受到攻击。由于车身总线数据的信息熵可以反映车身总线数据的稳定状态,如果该信息熵超出预置范围,则说明车身总线数据处于不稳地状态,也即车身总线数据中有可能出现用于攻击的异常数据,因此,可以确定所述车身总线受到攻击,并发出告警信息,以使用户尽早采取措施制止攻击的深入发展,进而提高用户的行车安全以及信息安全。
在本申请的一种可选实施例中,所述安全检测规则还可以为:监控所述 车身总线数据中的车身状态参数值是否处于异常状态,若所述车身状态参数值处于异常状态,则确定所述车身总线受到攻击,发出告警信息。参照图2,示出了根据本申请一个实施例的一种车辆攻击检测方法的步骤流程图,具体可以包括如下步骤:
步骤201、采集车身总线数据;
步骤202、确定所述车身总线数据对应的信息熵;
步骤203、若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息;
步骤204、判断所述车身总线数据中的车身状态参数值是否处于异常状态;
步骤205、若所述车身状态参数值处于异常状态,则确定所述车身总线受到攻击,发出告警信息。
需要说明的是,本申请实施例对于上述步骤202-步骤203、与步骤204-步骤205之间的执行顺序不加以限制。例如,可以先执行步骤202-步骤203,再执行步骤204-步骤205;或者先执行步骤204-步骤205,再执行步骤202-步骤203;或者并列同时执行步骤202-步骤203、与步骤204-步骤205均可。
在车辆启动后,车身各个ECU(Electronic Control Unit,电子控制单元)便开始相继启动工作,车身总线中也开始出现描述车身参数的数据,以下称为车身状态参数值。在本申请的一种可选实施例中,所述车身状态参数值至少包括如下参数值:车速、转速、迈速、挡位、油量、水温。
本申请实施例可以提供判断所述车身总线数据中的车身状态参数值是否处于异常状态的如下可选方案。
方案一
在具体应用中,攻击者在对车辆进行攻击时,在初期的攻击尝试阶段,往往是针对车辆某个功能模块单独进行尝试攻击。因此,本方案通过判断单个车身状态参数值是否处于异常状态,可以在攻击初期检测出车辆是否受到攻击,以及时发出告警信息,尽早减少用户的损失。
具体地,所述判断所述车身总线数据中的车身状态参数值是否处于异常 状态的步骤,可以包括:将所述车身状态参数值与正常参数值进行比对,若所述车身状态参数值与所述正常参数值的差异超出预设阈值,则确定所述车身状态参数值处于异常状态。
例如,检测出当前转速明显超出正常转速,或者,当前水温明显超出正常水温等,可以确定所述车身状态参数值处于异常状态。
方案二
在车辆行驶过程中,所获得的车身状态参数值之间并不是严格独立的,而是相互之间存在着一定的关联关系。比如迈速的取值范围与转速和挡位存在关联关系,水温的高低与转速、外部气温、行车时间也存在关联关系等。因此,方案二通过对具有关联关系的车身状态参数值进行检测,以判断车身总线是否受到攻击,进一步提高攻击检测的准确性。
具体地,所述判断所述车身总线数据中的车身状态参数值是否处于异常状态的步骤,可以包括:
步骤S21、判断具有关联关系的车身状态参数值是否分别符合对应的正常范围;
步骤S22、若具有关联关系的车身状态参数值中有至少一个参数值不符合对应的正常范围,则确定所述车身状态参数值处于异常状态。
例如,车速、转速以及挡位通常具有关联关系,在档位为X档、车速在M0-N0km/s范围内时,对应的正常转速应该在M1-N1 RPM范围内,如果检测出当前转速超出M1-N1 RPM的正常范围,则可以确定车身状态参数值处于异常状态。或者,检测出当前车速超出M0-N0KM/S的正常范围,则可以确定车身状态参数值处于异常状态。
可以理解,上述方案一和方案二所提供的判断车身状态参数值是否处于异常状态的方式仅作为本申请的可选实施例,在实际应用中,可以根据实际情况采取不同的判断方式。可选地,还可以通过检测预设时间内车身状态参数值是否处于稳定状态,来判断车身状态参数值是否处于异常状态;例如,若在短时间内检测到油量出现忽高忽低的不稳定状态,则可以确定车身状态参数值处于异常状态。
可选地,还可以通过检测仪表盘是否出现不正常的显示值,来判断车身状态参数值是否处于异常状态。例如,在车辆没有点火的情况下,仪表盘却显示有一定的转速或者迈速等,则可以确定车身状态参数值处于异常状态。
方案三
本方案可以收集大多数用户在正常驾驶过程中的车身状态参数值样本,所述车身状态参数值样本可以包括:正常的车身状态参数值样本也即正样本、以及异常的车身状态参数值样本也即反样本,依据上述正样本和反样本中车身状态参数值之间的关联关系得到特征向量,并且利用上述特征向量对正样本和反样本进行训练,通过机器学习的方式训练出状态检测模型,利用该状态检测模型判断车身总线数据中的车身状态参数值是否处于异常状态。由于该状态检测模型可以通过收集的大量车身状态参数值样本训练得到,因此,利用该状态检测模型具备正常状态或者异常状态的分类和识别能力,故可以提高检测攻击的准确性。
具体地,所述判断所述车身总线数据中的车身状态参数值是否处于异常状态的步骤,可以包括:
步骤S31、将所述车身状态参数值输入状态检测模型;所述状态检测模型为根据收集的车身状态参数值样本进行训练所得到;
步骤S32、若所述状态检测模型的输出结果为异常状态,则确定所述车身状态参数值处于异常状态。
可以理解,本申请实施例对于所述状态检测模型的具体训练方式不加以限制。例如,可以采集预设时间段内的车速、转速、挡位、转向角度、水温、油温等车身状态参数值作为车身状态参数值样本,对车身状态参数值样本进行归一化处理,将归一化后的数据分别采用BP(Error Back Propagation,误差反向传播)等算法训练神经网络获得最优模型参数,得到状态检测模型。
在本申请的一种可选实施例中,所述状态检测模型可以设置在云服务器中,所述将所述车身状态参数值输入状态检测模型的步骤,具体可以包括:
将所述车身状态参数值上传至所述云服务器,以将所述车身状态参数值输入所述云服务器中的状态检测模型进行异常状态检测。
在具体应用中,可以利用车联网设备采集车身状态参数值,并且上传至云服务器,云服务器利用车联网设备采集的车身状态参数值,依托大数据建立用于检测车辆安全状态的状态检测模型,可以对车辆运行过程中的实时采集的车身状态参数值进行分析,一旦发现车身状态参数值处于异常状态,即可发出告警,从而可以及时发现车身总线受到攻击并及早采取措施制止攻击的深入发展,降低用户的损失。
进一步地,云服务器可以将所述状态检测模型下发至车辆的车联网设备中,使得在车辆本地即可利用所述状态检测模型检测车身总线数据是否受到攻击。车联网设备还可以将实时采集的车身状态参数值以及检测结果发送至云服务器,以使云服务器可以对所述状态检测模型进行不断优化。
在具体应用中,由于不同用户具有不同的驾驶习惯,例如有的用户习惯在驾驶过程中急加速和急减速,这样,利用上述根据车辆正常行驶过程中采集的车身状态参数值样本训练得到的状态检测模型进行检测,有可能检测得到车身状态参数值处于异常状态,为了使得状态检测模型能够符合不同用户的驾驶习惯,在本申请的一种可选实施例中,所述方法还可以包括如下步骤:
步骤S41、收集用户的驾驶行为数据;
步骤S42、根据所述用户的驾驶行为数据对所述状态检测模型进行调整,以得到符合用户驾驶习惯的状态检测模型。
本申请实施例可以根据不同用户的驾驶行为数据,对所述状态检测模型的训练样本进行调整,以得到符合用户驾驶习惯的个性化状态检测模型。例如,转速的高低、急加速、急减速的次数可以反映用户的驾驶激烈程度等。对于驾驶行为较为激烈的用户,可以将稍大一些的车速、转速等车身状态参数值作为正样本,由此训练出的该用户的个性化状态检测模型可以符合用户的驾驶习惯,可以识别出属于该用户驾驶习惯的正常车身状态参数值,以及识别出属于车身总线攻击的异常车身状态参数值。
在实际应用中,本领域技术人员可以根据需要灵活选取上述三种方案中的任意一种或者任意组合。例如对于简单规则的判定(如方案一和方案二),可直接在车联网设备中进行判定,而对于需要大数据分析的复杂规则(如方 案三),可以通过车联网设备采集车身状态参数值上传至云服务器进行学习训练,再将经过学习训练生成的状态检测模型下发到车联网设备中进行使用。
在实际应用中,有可能出现由于车辆自身故障导致车辆异常的情况,因此,在本申请的一种可选实施例中,在所述车身总线数据对应的信息熵超出预置范围,或者所述车身状态参数值处于异常状态时,可以发出遭受攻击的告警信息;然而,此种情况下若通过修理厂检测等物理检测手段确定车身总线实际上并未受到攻击,则说明攻击检测结果有误,车辆有可能发生其它故障,此时可以生成故障检测报告。并且可以将所述车身总线数据、车身状态参数值以及故障检测结果上传至云服务器进行大数据分析,以进一步优化安全检测规则以及状态检测模型,从而可以减少攻击误判的几率,提高攻击检测的准确性。
综上,本申请实施例除了可以通过检测车身总线数据的信息熵来判断车身总线是否受到攻击,还可以通过检测车身总线数据中的车身状态参数值是否处于异常状态,来判断车身总线是否受到攻击。例如,通过判断单个车身状态参数值是否处于异常状态,可以在攻击初期检测出车辆是否受到攻击,以及时发出告警信息,尽早减少用户的损失。或者,通过对具有关联关系的车身状态参数值进行检测,以判断车身总线是否受到攻击,进一步提高攻击检测的准确性。再者,还可以通过状态检测模型检测车身总线是否受到攻击,不仅可以提高检测的准确性,还可以使得检测结果符合不同用户的驾驶习惯。
参照图3,示出了根据本申请一个实施例的一种车辆攻击检测装置的结构框图,具体可以包括如下模块:
数据采集模块301,用于采集车身总线数据;
信息熵确定模块302,用于确定所述车身总线数据对应的信息熵;
第一攻击确定模块303,用于若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息。
在本申请的一种可选实施例中,所述信息熵确定模块302,具体可以包括:
数据量获取子模块,用于获取预设时间段内所述车身总线数据中车身状态参数值的数据量和所述车身总线数据的总数据量;
信息熵确定子模块,用于根据所述车身状态参数值的数据量和所述车身总线数据的总数据量,确定所述车身总线数据对应的信息熵。
在本申请的另一种可选实施例中,所述装置还可以包括:
异常状态判断模块,用于判断所述车身总线数据中的车身状态参数值是否处于异常状态;
第二攻击确定模块,用于若所述车身状态参数值处于异常状态,则确定所述车身总线受到攻击,发出告警信息。
在本申请的又一种可选实施例中,所述异常状态判断模块,具体可以包括:
第一判断子模块,用于将所述车身状态参数值与正常参数值进行比对,若所述车身状态参数值与所述正常参数值的差异超出预设阈值,则确定所述车身状态参数值处于异常状态。
在本申请的再一种可选实施例中,所述异常状态判断模块,具体可以包括:
第二判断子模块,用于判断具有关联关系的车身状态参数值是否分别符合对应的正常范围;
异常确定子模块,用于若具有关联关系的车身状态参数值中有至少一个参数值不符合对应的正常范围,则确定所述车身状态参数值处于异常状态。
在本申请的再一种可选实施例中,所述异常状态判断模块,具体可以包括:
模型输入子模块,用于将所述车身状态参数值输入状态检测模型;所述状态检测模型为根据收集的车身状态参数值样本进行训练所得到;
结果输出子模块,用于若所述状态检测模型的输出结果为异常状态,则确定所述车身状态参数值处于异常状态。
在本申请的再一种可选实施例中,所述装置还可以包括:
行为收集模块,用于收集用户的驾驶行为数据;
模型调整模块,用于根据所述用户的驾驶行为数据对所述状态检测模型进行调整,以得到符合用户驾驶习惯的状态检测模型。
在本申请的再一种可选实施例中,所述状态检测模型设置在云服务器中,所述模型输入子模块,具体可以包括:
上传单元,用于将所述车身状态参数值上传至所述云服务器,以将所述车身状态参数值输入所述云服务器中的状态检测模型进行异常状态检测。
在本申请的再一种可选实施例中,所述车身状态参数值至少包括如下参数:车速、转速、迈速、挡位、油量、水温。
对于装置实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
本发明的各个部件实施例可以以硬件实现,或者以在一个或者多个处理器上运行的软件模块实现,或者以它们的组合实现。本领域的技术人员应当理解,可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本发明实施例的车辆攻击检测设备中的一些或者全部部件的一些或者全部功能。本发明还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如,计算机程序和计算机程序产品)。这样的实现本发明的程序可以存储在计算机可读介质上,或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到,或者在载体信号上提供,或者以任何其他形式提供。
例如,图4示出了可以实现根据本发明的车辆攻击检测的终端设备。该终端设备传统上包括处理器410和以存储器420形式的计算机程序产品或者计算机可读介质。存储器420可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器420具有用于执行上述方法中的任何方法步骤的程序代码431的存储空间430。例如,用于程序代码的存储空间430可以包括分别用于实现上面的方法中的各种步骤的各个程序代码431。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个 或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘,紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为如参考图5所述的便携式或者固定存储单元。该存储单元可以具有与图4的终端设备中的存储器420类似布置的存储段、存储空间等。程序代码可以例如以适当形式进行压缩。通常,存储单元包括计算机可读代码431’,即可以由例如诸如410之类的处理器读取的代码,这些代码当由终端设备运行时,导致该终端设备执行上面所描述的方法中的各个步骤。
本文中所称的“一个实施例”、“实施例”或者“一个或者多个实施例”意味着,结合实施例描述的特定特征、结构或者特性包括在本发明的至少一个实施例中。此外,请注意,这里“在一个实施例中”的词语例子不一定全指同一个实施例。
在此处所提供的说明书中,说明了大量具体细节。然而,能够理解,本发明的实施例可以在没有这些具体细节的情况下被实践。在一些实例中,并未详细示出公知的方法、结构和技术,以便不模糊对本说明书的理解。
应该注意的是上述实施例对本发明进行说明而不是对本发明进行限制,并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中,不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本发明可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中,这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
此外,还应当注意,本说明书中使用的语言主要是为了可读性和教导的目的而选择的,而不是为了解释或者限定本发明的主题而选择的。因此,在不偏离所附权利要求书的范围和精神的情况下,对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。对于 本发明的范围,对本发明所做的公开是说明性的,而非限制性的,本发明的范围由所附权利要求书限定。

Claims (20)

  1. 一种车辆攻击检测方法,其中,所述方法包括:
    采集车身总线数据;
    确定所述车身总线数据对应的信息熵;
    若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息。
  2. 如权利要求1所述的方法,其中,所述确定所述车身总线数据对应的信息熵的步骤,包括:
    获取预设时间段内所述车身总线数据中车身状态参数值的数据量和所述车身总线数据的总数据量;
    根据所述车身状态参数值的数据量和所述车身总线数据的总数据量,确定所述车身总线数据对应的信息熵。
  3. 如权利要求1所述的方法,其中,所述方法还包括:
    判断所述车身总线数据中的车身状态参数值是否处于异常状态;
    若所述车身状态参数值处于异常状态,则确定所述车身总线受到攻击,发出告警信息。
  4. 如权利要求3所述的方法,其中,所述判断所述车身总线数据中的车身状态参数值是否处于异常状态的步骤,包括:
    将所述车身状态参数值与正常参数值进行比对,若所述车身状态参数值与所述正常参数值的差异超出预设阈值,则确定所述车身状态参数值处于异常状态。
  5. 如权利要求3所述的方法,其中,所述判断所述车身总线数据中的车身状态参数值是否处于异常状态的步骤,包括:
    判断具有关联关系的车身状态参数值是否分别符合对应的正常范围;
    若具有关联关系的车身状态参数值中有至少一个参数值不符合对应的正常范围,则确定所述车身状态参数值处于异常状态。
  6. 如权利要求3所述的方法,其中,所述判断所述车身总线数据中的车身状态参数值是否处于异常状态的步骤,包括:
    将所述车身状态参数值输入状态检测模型;所述状态检测模型为根据收 集的车身状态参数值样本进行训练所得到;
    若所述状态检测模型的输出结果为异常状态,则确定所述车身状态参数值处于异常状态。
  7. 如权利要求6所述的方法,其中,所述方法还包括:
    收集用户的驾驶行为数据;
    根据所述用户的驾驶行为数据对所述状态检测模型进行调整,以得到符合用户驾驶习惯的状态检测模型。
  8. 如权利要求6所述的方法,其中,所述状态检测模型设置在云服务器中,所述将所述车身状态参数值输入状态检测模型的步骤,包括:
    将所述车身状态参数值上传至所述云服务器,以将所述车身状态参数值输入所述云服务器中的状态检测模型进行异常状态检测。
  9. 如权利要求2至8所述的方法,其中,所述车身状态参数值至少包括如下参数:车速、转速、迈速、挡位、油量、水温。
  10. 一种车辆攻击检测装置,所述装置包括:
    数据采集模块,用于采集车身总线数据;
    信息熵确定模块,用于确定所述车身总线数据对应的信息熵;
    第一攻击确定模块,用于若所述信息熵超出预置范围,则确定所述车身总线受到攻击,发出告警信息。
  11. 如权利要求10所述的装置,其中,所述信息熵确定模块,包括:
    数据量获取子模块,用于获取预设时间段内所述车身总线数据中车身状态参数值的数据量和所述车身总线数据的总数据量;
    信息熵确定子模块,用于根据所述车身状态参数值的数据量和所述车身总线数据的总数据量,确定所述车身总线数据对应的信息熵。
  12. 如权利要求10所述的装置,其中,所述装置还包括:
    异常状态判断模块,用于判断所述车身总线数据中的车身状态参数值是否处于异常状态;
    第二攻击确定模块,用于若所述车身状态参数值处于异常状态,则确定 所述车身总线受到攻击,发出告警信息。
  13. 如权利要求12所述的装置,其中,所述异常状态判断模块,包括:
    第一判断子模块,用于将所述车身状态参数值与正常参数值进行比对,若所述车身状态参数值与所述正常参数值的差异超出预设阈值,则确定所述车身状态参数值处于异常状态。
  14. 如权利要求12所述的装置,其中,所述异常状态判断模块,包括:
    第二判断子模块,用于判断具有关联关系的车身状态参数值是否分别符合对应的正常范围;
    异常确定子模块,用于若具有关联关系的车身状态参数值中有至少一个参数值不符合对应的正常范围,则确定所述车身状态参数值处于异常状态。
  15. 如权利要求12所述的装置,其中,所述异常状态判断模块,包括:
    模型输入子模块,用于将所述车身状态参数值输入状态检测模型;所述状态检测模型为根据收集的车身状态参数值样本进行训练所得到;
    结果输出子模块,用于若所述状态检测模型的输出结果为异常状态,则确定所述车身状态参数值处于异常状态。
  16. 如权利要求15所述的装置,其中,所述装置还包括:
    行为收集模块,用于收集用户的驾驶行为数据;
    模型调整模块,用于根据所述用户的驾驶行为数据对所述状态检测模型进行调整,以得到符合用户驾驶习惯的状态检测模型。
  17. 如权利要求15所述的装置,其中,所述状态检测模型设置在云服务器中,所述模型输入子模块,包括:
    上传单元,用于将所述车身状态参数值上传至所述云服务器,以将所述车身状态参数值输入所述云服务器中的状态检测模型进行异常状态检测。
  18. 如权利要求11至17所述的装置,其中,所述车身状态参数值至少包括如下参数:车速、转速、迈速、挡位、油量、水温。
  19. 一种计算机程序,包括计算机可读代码,当所述计算机可读代码在终端设备上运行时,导致所述终端设备执行根据权利要求1-9中的任一个所述的车辆攻击检测方法。
  20. 一种计算机可读介质,其中存储了如权利要求19所述的计算机程序。
PCT/CN2017/119413 2016-12-28 2017-12-28 一种车辆攻击检测方法和装置 WO2018121675A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611239362.1A CN106650505A (zh) 2016-12-28 2016-12-28 一种车辆攻击检测方法和装置
CN201611239362.1 2016-12-28

Publications (1)

Publication Number Publication Date
WO2018121675A1 true WO2018121675A1 (zh) 2018-07-05

Family

ID=58835323

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/119413 WO2018121675A1 (zh) 2016-12-28 2017-12-28 一种车辆攻击检测方法和装置

Country Status (2)

Country Link
CN (1) CN106650505A (zh)
WO (1) WO2018121675A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111726774A (zh) * 2020-06-28 2020-09-29 北京百度网讯科技有限公司 防御攻击的方法、装置、设备及存储介质
CN112653654A (zh) * 2019-10-12 2021-04-13 深圳市奇虎智能科技有限公司 安全监控方法、装置、计算机设备及存储介质
CN113163369A (zh) * 2020-01-20 2021-07-23 北京新能源汽车股份有限公司 一种车辆入侵防御处理方法、装置及汽车
CN113347134A (zh) * 2020-02-18 2021-09-03 国家计算机网络与信息安全管理中心浙江分中心 针对车联网tsp平台的攻击检测方法及系统

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106650505A (zh) * 2016-12-28 2017-05-10 北京奇虎科技有限公司 一种车辆攻击检测方法和装置
CN107356821B (zh) * 2017-06-07 2019-08-16 中国科学院信息工程研究所 一种车辆信息安全检测的装置及车辆检测方法
CN107566347B (zh) * 2017-08-10 2020-07-24 北京梆梆安全科技有限公司 滚动码学习检测方法及装置、设备和计算机可读存储介质
CN107566402B (zh) * 2017-10-13 2020-08-04 成都信息工程大学 基于soeks的车载电子信息系统入侵检测方法与实现
CN108183954A (zh) * 2017-12-28 2018-06-19 北京奇虎科技有限公司 一种车辆安全的检测方法及装置
CN108173856A (zh) * 2017-12-28 2018-06-15 北京奇虎科技有限公司 车辆通信数据安全检测方法、装置及车载终端
CN108200042A (zh) * 2017-12-28 2018-06-22 北京奇虎科技有限公司 一种车辆安全的检测方法及车辆安全管理平台
US10887349B2 (en) * 2018-01-05 2021-01-05 Byton Limited System and method for enforcing security with a vehicle gateway
CN110389572A (zh) * 2018-04-23 2019-10-29 上海博泰悦臻电子设备制造有限公司 车辆零件故障提前预警方法、系统及服务器
WO2019229969A1 (ja) * 2018-06-01 2019-12-05 三菱電機株式会社 データ通信制御装置、データ通信制御プログラムおよび車両制御システム
CN108923904A (zh) * 2018-06-29 2018-11-30 百度在线网络技术(北京)有限公司 汽车指令处理方法、装置、设备、云平台及存储介质
US11036561B2 (en) * 2018-07-24 2021-06-15 Oracle International Corporation Detecting device utilization imbalances
CN109117632B (zh) * 2018-07-27 2021-05-07 北京梆梆安全科技有限公司 一种确定车辆被入侵之风险的方法和装置
CN109117639B (zh) * 2018-07-27 2021-03-16 北京梆梆安全科技有限公司 一种入侵风险的检测方法和装置
CN109347823B (zh) * 2018-10-17 2021-04-09 湖南汽车工程职业学院 一种基于信息熵的can总线异常检测方法
CN109375609B (zh) * 2018-10-18 2021-02-02 北京鼎力信安技术有限公司 异常攻击的检测方法及装置
CN111447166B (zh) * 2018-12-29 2022-11-04 北京奇虎科技有限公司 车辆攻击检测方法及装置
CN109878341B (zh) * 2019-03-07 2020-04-14 广东轻工职业技术学院 新能源车辆智能网络控制方法及其系统
CN110275508B (zh) * 2019-05-08 2021-09-28 西安电子科技大学 车载can总线网络异常检测方法及系统
CN114978579A (zh) * 2022-04-08 2022-08-30 联合汽车电子有限公司 一种信息处理方法、异常检测装置、介质及车载控制器

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014061021A1 (en) * 2012-10-17 2014-04-24 Tower-Sec Ltd. A device for detection and prevention of an attack on a vehicle
CN103873319A (zh) * 2012-12-12 2014-06-18 现代自动车株式会社 用于检测车内网络攻击的装置与方法
CN105828333A (zh) * 2016-05-11 2016-08-03 北京航空航天大学 一种基于车辆自组织网络流量异常的黑客车辆检测方法
CN106184068A (zh) * 2016-06-30 2016-12-07 北京奇虎科技有限公司 汽车内部网络安全检测方法及装置、汽车
CN106650505A (zh) * 2016-12-28 2017-05-10 北京奇虎科技有限公司 一种车辆攻击检测方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014061021A1 (en) * 2012-10-17 2014-04-24 Tower-Sec Ltd. A device for detection and prevention of an attack on a vehicle
CN103873319A (zh) * 2012-12-12 2014-06-18 现代自动车株式会社 用于检测车内网络攻击的装置与方法
CN105828333A (zh) * 2016-05-11 2016-08-03 北京航空航天大学 一种基于车辆自组织网络流量异常的黑客车辆检测方法
CN106184068A (zh) * 2016-06-30 2016-12-07 北京奇虎科技有限公司 汽车内部网络安全检测方法及装置、汽车
CN106650505A (zh) * 2016-12-28 2017-05-10 北京奇虎科技有限公司 一种车辆攻击检测方法和装置

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112653654A (zh) * 2019-10-12 2021-04-13 深圳市奇虎智能科技有限公司 安全监控方法、装置、计算机设备及存储介质
CN113163369A (zh) * 2020-01-20 2021-07-23 北京新能源汽车股份有限公司 一种车辆入侵防御处理方法、装置及汽车
CN113347134A (zh) * 2020-02-18 2021-09-03 国家计算机网络与信息安全管理中心浙江分中心 针对车联网tsp平台的攻击检测方法及系统
CN113347134B (zh) * 2020-02-18 2022-07-19 国家计算机网络与信息安全管理中心浙江分中心 针对车联网tsp平台的攻击检测方法及系统
CN111726774A (zh) * 2020-06-28 2020-09-29 北京百度网讯科技有限公司 防御攻击的方法、装置、设备及存储介质
CN111726774B (zh) * 2020-06-28 2023-09-05 阿波罗智联(北京)科技有限公司 防御攻击的方法、装置、设备及存储介质
US11797674B2 (en) 2020-06-28 2023-10-24 Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. Method and apparatus for defending against attacks, device and storage medium

Also Published As

Publication number Publication date
CN106650505A (zh) 2017-05-10

Similar Documents

Publication Publication Date Title
WO2018121675A1 (zh) 一种车辆攻击检测方法和装置
CN111131185B (zh) 基于机器学习的can总线网络异常检测方法及装置
Zhang et al. Intrusion detection system using deep learning for in-vehicle security
US11748474B2 (en) Security system and methods for identification of in-vehicle attack originator
Levi et al. Advanced analytics for connected car cybersecurity
US10382466B2 (en) Cooperative cloud-edge vehicle anomaly detection
CN111771371B (zh) 用于在线实时多对象跟踪的系统和方法
US20210176254A1 (en) Authenticating Drivers
CN106559431B (zh) 一种用于汽车安全检测的可视化分析方法和装置
Guo et al. Detecting vehicle anomaly in the edge via sensor consistency and frequency characteristic
EP3776367A1 (en) Detecting data anomalies on a data interface using machine learning
Xun et al. VehicleEIDS: A novel external intrusion detection system based on vehicle voltage signals
WO2020140897A1 (en) Detecting vehicle intrusion using command pattern models
US11539724B2 (en) Centralized detection techniques for cyber-attacks directed at connected vehicles
Bozdal et al. WINDS: A wavelet-based intrusion detection system for controller area network (CAN)
US20210114534A1 (en) Vehicle security enhancement
Narayanan et al. Security in smart cyber-physical systems: a case study on smart grids and smart cars
CN111447166B (zh) 车辆攻击检测方法及装置
CN112671724B (zh) 一种终端安全检测分析方法、装置、设备及可读存储介质
CN114900331B (zh) 基于can报文特征的车载can总线入侵检测方法
Daily et al. Towards a cyber assurance testbed for heavy vehicle electronic controls
KR101791786B1 (ko) 자동차 보안 시스템 및 그 동작 방법
CN104134248A (zh) 一种危险驾驶行为监测方法及系统
CN106487630A (zh) 一种基于测试用例检测汽车安全性的方法和装置
Wei et al. IoVShield: an efficient vehicular intrusion detection system for self-driving (short paper)

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: 17887901

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17887901

Country of ref document: EP

Kind code of ref document: A1