CN115016433A - Vehicle-mounted CAN bus flow abnormity detection method and system - Google Patents
Vehicle-mounted CAN bus flow abnormity detection method and system Download PDFInfo
- Publication number
- CN115016433A CN115016433A CN202210615083.XA CN202210615083A CN115016433A CN 115016433 A CN115016433 A CN 115016433A CN 202210615083 A CN202210615083 A CN 202210615083A CN 115016433 A CN115016433 A CN 115016433A
- Authority
- CN
- China
- Prior art keywords
- bus
- flow
- sub
- data
- vehicle
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000013528 artificial neural network Methods 0.000 claims description 27
- 230000005856 abnormality Effects 0.000 claims description 10
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 10
- 230000006872 improvement Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004092 self-diagnosis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L2012/40208—Bus networks characterized by the use of a particular bus standard
- H04L2012/40215—Controller Area Network CAN
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L2012/40267—Bus for use in transportation systems
- H04L2012/40273—Bus for use in transportation systems the transportation system being a vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Automation & Control Theory (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Small-Scale Networks (AREA)
Abstract
A vehicle CAN bus flow abnormity detection method and system comprises the steps of obtaining flow data of a CAN bus and conducting preliminary preprocessing; transmitting the processed flow data to a plurality of control units for sub-network learning; the abnormal flow data is identified according to the learning condition of the sub-network, the technical problem of poor detection performance and timeliness existing in the conventional abnormal detection method is solved, and the method effectively utilizes the multi-view effect of the parallel structure to realize the remarkable improvement of the detection capability, so that the quick and accurate abnormal flow detection effect is achieved, and the method can be widely applied to the field of big data processing.
Description
Technical Field
The invention relates to the field of big data processing, in particular to a method and a system for detecting abnormal traffic of a vehicle-mounted CAN bus.
Background
With the development of mobile communication technology and internet of things technology, internet of vehicles communication and vehicle-mounted network have been widely applied to key functions of emerging intelligent traffic systems, and have become a popular trend of current information society.
The vehicle-mounted Controller Area Network (CAN) is a protocol based on message broadcasting, wherein the CAN messages do not contain node information of a sender and a receiver, and a priority scheme based on ID messages is adopted to transmit the messages, so that the related Electronic Control Units (ECUs) CAN realize rapid and efficient data exchange, and the communication channel is prevented from being excessively crowded. However, the CAN messages therefore lack authentication information and the communication information is not encrypted, making it easy for an attacker to attack and intrude on the CAN traffic. Therefore, the abnormal detection technology of the CAN flow is a vital safety guarantee for vehicles and passengers.
Through research, various anomaly detection technologies of the existing vehicle-mounted network mainly aim at improving detection effects, such as detection accuracy, precision and recall rate, false alarm rate reduction and the like. Most of the existing vehicle-mounted CAN bus flow abnormity detection methods are based on a deep convolutional neural network or a cyclic neural network model, the number of neural network layers is large, parameters are various, the model volume is large, and resource consumption of computing equipment is huge. If the method is directly applied to a vehicle-mounted CAN bus system of a networked vehicle, ECU equipment operating the method CAN bear heavy burden and even completely lose functions, namely, the method operating on limited calculation resources of an ECU in the vehicle not only greatly reduces the detection performance of a model, but also even causes the function abnormality of the vehicle-mounted CAN bus system. Therefore, the prior art method does not effectively utilize the natural advantages of parallel resources of a vehicle-mounted CAN bus equipped with hundreds of ECUs, and is difficult to meet the requirement of running vehicles on the timeliness of the CAN flow anomaly detection technology.
Disclosure of Invention
The application aims to provide a vehicle-mounted CAN bus flow abnormity detection method and system, and aims to solve the technical problems of poor detection performance and timeliness of the traditional abnormity detection method.
A first aspect of an embodiment of the present application provides a method for detecting traffic abnormality of a vehicle-mounted CAN bus, including:
acquiring flow data of a CAN bus and performing primary pretreatment;
transmitting the processed flow data to a plurality of control units for sub-network learning;
the anomalous traffic data is identified based on the sub-network learning condition.
Preferably, the method for acquiring the flow data of the CAN bus and performing preliminary pretreatment comprises the following steps:
reading the flow data of the CAN bus;
preprocessing the flow data;
and preliminarily extracting the data characteristics of the flow data.
Preferably, the processed flow data is transmitted to a plurality of control units, and a system resource adaptation algorithm is adopted to distribute a plurality of shallow sub-neural network structures to the plurality of control units for operation.
Preferably, the system resource adaptation algorithm is specifically implemented by the following means:
constructing a mathematical model: let i
The idle rate of the processor when the control unit normally operates is C i Memory idle rate of M i Comprehensively evaluating the resource vacancy rate of the ECU as S i The definition is as follows:
the risk index is used as the importance index of the module and is set as R i (R i Is a positive integer not exceeding 10), the higher the index is, the higher the importance is, the branch neural network module is not suitable to be distributed; thus, a comprehensive availability index U of the ith control unit is defined i The following were used:
wherein, alpha is a positive integer coefficient and is used for adjusting the balance between the importance and the resource vacancy rate;
according to the modeling result, a threshold value H is given to judge whether the control unit has enough availability for installing the branch shallow neural network module; if U is present i And if not, any branch network module is not selected to be installed on the control unit.
Preferably, the sub-network learning is performed by downsampling with different dimensions, and then the neural network structure is used to extract features.
Preferably, the feature extraction of the neural network structure is performed by using a depth separable convolution operation.
Preferably, the method for identifying abnormal traffic data according to the learning condition of the sub-network comprises the following steps:
performing feature fusion on each data feature obtained by sub-network learning;
carrying out feature classification on the fused features;
and carrying out anomaly detection processing to identify the abnormal flow data.
A second aspect of the present application provides an on-vehicle CAN bus flow anomaly detection system, including:
a flow acquisition module: the system is used for acquiring the flow data of the CAN bus and performing primary pretreatment;
a flow learning module: the system is used for transmitting the processed flow data to a plurality of control units for sub-network learning;
a flow identification module: for identifying abnormal traffic data based on sub-network learning conditions.
The invention fully utilizes the natural resource advantage that hundreds of ECUs are assembled on the vehicle-mounted CAN bus, realizes multi-dimensional feature learning of CAN bus flow data and comprehensive learning result by dynamically adapting to a plurality of ECUs for parallel operation of the feature learning substructure, effectively utilizes the multi-view effect of the parallel structure to realize remarkable improvement of detection capability, and thus achieves the effect of quickly and accurately detecting abnormal flow. The method has strong generalization capability, can be used in similar scenes of various flow anomaly detection, and overcomes the defects of overlarge depth, overhigh computation complexity, excessively slow running speed and the like of a feature learning model.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting abnormal traffic of a vehicle-mounted CAN bus according to an embodiment of the present application;
fig. 2 is a schematic diagram of a detection principle of a vehicle-mounted CAN bus flow anomaly detection method according to an embodiment of the present application.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that the terms "upper", "lower", "inner", "outer", "top", "bottom", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and are not to be construed as indicating or implying that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
The method replaces the linear neural network structure in the prior art by adopting a parallel sub-neural network structure, wherein each sub-neural network structure is composed of a data down-sampling module and a simple neural network structure with a low number of layers (for example, no more than 10 layers). In order to ensure that the learned characteristics CAN fully reflect the data characteristics of CAN flow and achieve high-accuracy abnormal flow identification, the method and the device adopt downsampling processing modules with different dimensions for each sub-network structure, so that flow data characteristics CAN be comprehensively obtained from multiple data dimensions and multiple extraction degrees. Through different down-sampling processing of the sub-neural networks, the number of characteristic channels reserved by the processed data is different, and the data quantity and the processing time length required to be processed by each sub-neural network are different. The higher the extraction degree, the smaller the number of channels reserved, the smaller the amount of data that the sub-neural network needs to process, and the shorter the running time.
The embodiment specifically comprises a vehicle-mounted CAN bus system resource adaptation component and a parallel feature learning component based on the characteristics of multiple control units of a vehicle-mounted CAN bus, wherein the two main functional components are as follows:
referring to fig. 1, a schematic flow chart of a method for detecting abnormal traffic of a vehicle-mounted CAN bus according to an embodiment of the present application is shown, and for convenience of description, only parts related to the embodiment are shown, which is detailed as follows:
in one embodiment, a method for detecting traffic abnormality of a vehicle-mounted CAN bus includes:
s101, acquiring flow data of the CAN bus and performing primary pretreatment.
Specifically, as shown in fig. 2, the flow data of the CAN bus is read by a central electronic module (vehicle-mounted self-diagnosis system), the flow data is preprocessed, and the data feature of the flow data is preliminarily extracted.
And S102, transmitting the processed flow data to a plurality of control units for sub-network learning.
Specifically, in order to fully utilize numerous ECU resources in a vehicle, improve the running speed of detection and simultaneously improve the detection capability by utilizing the multi-view effect of a parallel structure, n (n is more than or equal to 20) shallow sub-neural network structures are respectively distributed to n ECUs for running; in fact, different ECU resources in the vehicle have different usage rates and importance levels, for example, the usage rate and importance of the ECU resource responsible for controlling the driving system are obviously higher than those of the ECU resource responsible for controlling the window and door system. In order to effectively utilize ECU resources and not interfere with the operation efficiency of the original control program, the application designs a corresponding system resource adaptation algorithm, quantitatively analyzes the importance and the resource quantity of each ECU module, and constructs the following mathematical model:
let i
The idle rate of the processor when the ECU operates normally is C i Memory idle rate of M i Comprehensively evaluating the resource vacancy rate of the ECU as S i The definition is as follows:
the automobile manufacturer can rate the risk of a module system in an automobile and represent the risk level which is possibly caused by the module if the module fails, and the method takes the risk index as the importance index of the module and sets the importance index as R i (in general R) i A positive integer not exceeding 10), a higher index indicates a higher importance, and it is not appropriate to assign a branch neural network module. Therefore, a comprehensive availability index U of the ith ECU is defined i The following were used:
wherein, α is a positive integer coefficient for adjusting the balance between the importance and the resource vacancy rate.
According to the modeling result, a threshold value H is given to judge whether the ECU has enough availability for installing the branch shallow neural network module; if U is present i And if not, any branch network module is not selected to be installed on the ECU.
In the embodiment, the parallel feature learning component based on the multi-ECU characteristics of the vehicle-mounted CAN bus is adopted to realize the anomaly detection:
firstly, downsampling processing of different dimensionalities is carried out in each sub-network, and then features are extracted by using a neural network structure; in order to ensure the lightweight of a subnetwork structure, reduce the occupation of ECU resources and improve the running speed of a model, the method adopts representative depth separable convolution (DW) operation to extract features, and the convolution network structure has lower parameter and operation cost compared with the conventional convolution operation; in fact, each branch neural network module can adapt to various neural network structures according to the actual conditions of the ECU resource condition where the branch neural network module is located, the performance requirement of feature extraction and the like, and is not limited to DW convolution operation; for example, a certain branch may adopt a conventional convolution operation to extract spatial features of data, while another branch may also use a recurrent neural network structure to consider time series features of data, thereby achieving a multi-view extraction effect.
And S103, identifying abnormal flow data according to the learning condition of the sub-network.
Specifically, the data features learned by each sub-network are transmitted back to the central electronic module for feature fusion, and the fused features are classified; if the abnormal flow data is identified, the central electronic module can immediately send an alarm and perform abnormal processing.
According to the method, the system load is dynamically distributed to the plurality of ECUs according to the real-time resource occupation condition of the vehicle-mounted ECU to perform parallel calculation of the plurality of branches, each branch adopts a shallow neural network structure, the operation load of an abnormality detection module of each ECU is reduced, the problems that the existing method is low in operation speed, high in calculation complexity, incapable of fully utilizing ECU resources in a vehicle and the like are solved, and the abnormal detection of CAN bus flow is achieved.
The second aspect of the application provides a vehicle-mounted CAN bus flow abnormity detection system, which comprises a flow acquisition module, a flow learning module and a flow identification module.
A flow acquisition module: the system is used for acquiring the flow data of the CAN bus and performing primary pretreatment;
a flow learning module: the system is used for transmitting the processed flow data to a plurality of control units for sub-network learning;
a flow identification module: for identifying abnormal traffic data based on sub-network learning conditions.
It should be noted that, a vehicle-mounted CAN bus traffic abnormality detection system in this embodiment is an embodiment of a system corresponding to the vehicle-mounted CAN bus traffic abnormality detection method, and therefore, for specific implementation of software methods in modules of the traffic abnormality detection system, reference may be made to the embodiments in fig. 1 to fig. 2, and details are not repeated here.
According to the method and the system for detecting the abnormal traffic of the vehicle-mounted CAN bus, disclosed by the embodiment of the invention, the advantage of natural resources of hundreds of ECUs assembled on the vehicle-mounted CAN bus is fully utilized, the multi-dimensional characteristic learning of CAN bus traffic data and the comprehensive learning result are realized by dynamically adapting the characteristic learning substructures to a plurality of ECUs for parallel operation, namely, the multi-view effect of the parallel structure is effectively utilized to realize the remarkable improvement of the detection capability, so that the quick and accurate abnormal traffic detection effect is realized. The method has strong generalization capability, can be used in similar scenes of various flow anomaly detection, and overcomes the defects of overlarge depth, overhigh computation complexity, excessively slow running speed and the like of a feature learning model.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (8)
1. A vehicle-mounted CAN bus flow abnormity detection method is characterized by comprising the following steps:
acquiring flow data of a CAN bus and performing primary pretreatment;
transmitting the processed flow data to a plurality of control units for sub-network learning;
abnormal traffic data is identified based on the sub-network learning condition.
2. The method for detecting the traffic abnormality of the vehicle-mounted CAN bus according to claim 1, wherein the method for acquiring the traffic data of the CAN bus and performing preliminary preprocessing comprises the following steps:
reading the flow data of the CAN bus;
preprocessing the flow data;
and preliminarily extracting the data characteristics of the flow data.
3. The method as claimed in claim 1, wherein the processed traffic data is transmitted to a plurality of control units, and a system resource adaptation algorithm is employed to distribute a plurality of shallow sub-neural network structures to the plurality of control units for operation.
4. The method for detecting traffic abnormality of the on-vehicle CAN bus according to claim 3, wherein the system resource adaptation algorithm is specifically implemented by:
constructing a mathematical model: is provided with the first
The idle rate of the processor when the control unit normally operates is C i Memory idle rate of M i Comprehensively evaluating the resource vacancy rate of the ECU as S i The definition is as follows:
the importance index of the module is set as R by taking the risk index i (R i Is a positive integer not exceeding 10), the higher the index is, the higher the importance is, the branch neural network module is not suitable to be distributed; thus, a comprehensive availability index U of the ith control unit is defined i The following were used:
wherein, alpha is a positive integer coefficient and is used for adjusting the balance between the importance and the resource vacancy rate;
according to the modeling result, a threshold value H is given to judge whether the control unit has enough availability for installing the branch shallow neural network module; if U is present i And if not, any branch network module is not selected to be installed on the control unit.
5. The method as claimed in claim 1, wherein the sub-network learning is performed by down-sampling with different dimensions and then extracting features by using a neural network structure.
6. The method of claim 5, wherein the feature extraction of the neural network structure is performed by a deep separable convolution operation.
7. The method for detecting traffic abnormality of on-vehicle CAN bus according to claim 1, wherein the step of identifying abnormal traffic data according to learning condition of sub-network comprises the steps of:
performing feature fusion on each data feature obtained by sub-network learning;
carrying out feature classification on the fused features;
and carrying out anomaly detection processing to identify the abnormal flow data.
8. The utility model provides an on-vehicle CAN bus flow anomaly detection system which characterized in that includes:
a flow acquisition module: the system is used for acquiring the flow data of the CAN bus and performing primary pretreatment;
a flow learning module: the system is used for transmitting the processed flow data to a plurality of control units for sub-network learning;
a flow identification module: for identifying abnormal traffic data based on sub-network learning conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210615083.XA CN115016433A (en) | 2022-06-01 | 2022-06-01 | Vehicle-mounted CAN bus flow abnormity detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210615083.XA CN115016433A (en) | 2022-06-01 | 2022-06-01 | Vehicle-mounted CAN bus flow abnormity detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115016433A true CN115016433A (en) | 2022-09-06 |
Family
ID=83070120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210615083.XA Pending CN115016433A (en) | 2022-06-01 | 2022-06-01 | Vehicle-mounted CAN bus flow abnormity detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115016433A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170024849A1 (en) * | 2015-07-23 | 2017-01-26 | Sony Corporation | Learning convolution neural networks on heterogeneous cpu-gpu platform |
| CN109639734A (en) * | 2019-01-24 | 2019-04-16 | 大连理工大学 | A kind of anomalous traffic detection method with computing resource adaptivity |
| CN109639739A (en) * | 2019-01-30 | 2019-04-16 | 大连理工大学 | A kind of anomalous traffic detection method based on autocoder network |
| CN111131185A (en) * | 2019-12-06 | 2020-05-08 | 中国电子科技网络信息安全有限公司 | CAN bus network anomaly detection method and device based on machine learning |
| US20210112091A1 (en) * | 2019-10-10 | 2021-04-15 | Charter Communications Operating, Llc | Denial-of-service detection and mitigation solution |
| KR20210043053A (en) * | 2019-10-10 | 2021-04-21 | 고려대학교 산학협력단 | Device and method for can traffic modeling and device and method for anomaly detection |
| US20210157683A1 (en) * | 2019-11-22 | 2021-05-27 | EMC IP Holding Company LLC | Method, device and computer program product for managing data backup |
| CN113259332A (en) * | 2021-04-29 | 2021-08-13 | 上海电力大学 | Multi-type network flow abnormity detection method and system based on end-to-end |
| CN113625681A (en) * | 2021-07-19 | 2021-11-09 | 湖南大学 | CAN bus abnormality detection method, system and storage medium |
| CN113746862A (en) * | 2021-09-14 | 2021-12-03 | 恒安嘉新（北京）科技股份公司 | Abnormal flow detection method, device and equipment based on machine learning |
| WO2021258348A1 (en) * | 2020-06-24 | 2021-12-30 | 深圳市欢太科技有限公司 | Abnormal flow detection method and system and computer storage medium |
-
2022
- 2022-06-01 CN CN202210615083.XA patent/CN115016433A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170024849A1 (en) * | 2015-07-23 | 2017-01-26 | Sony Corporation | Learning convolution neural networks on heterogeneous cpu-gpu platform |
| CN109639734A (en) * | 2019-01-24 | 2019-04-16 | 大连理工大学 | A kind of anomalous traffic detection method with computing resource adaptivity |
| CN109639739A (en) * | 2019-01-30 | 2019-04-16 | 大连理工大学 | A kind of anomalous traffic detection method based on autocoder network |
| US20210112091A1 (en) * | 2019-10-10 | 2021-04-15 | Charter Communications Operating, Llc | Denial-of-service detection and mitigation solution |
| KR20210043053A (en) * | 2019-10-10 | 2021-04-21 | 고려대학교 산학협력단 | Device and method for can traffic modeling and device and method for anomaly detection |
| US20210157683A1 (en) * | 2019-11-22 | 2021-05-27 | EMC IP Holding Company LLC | Method, device and computer program product for managing data backup |
| CN111131185A (en) * | 2019-12-06 | 2020-05-08 | 中国电子科技网络信息安全有限公司 | CAN bus network anomaly detection method and device based on machine learning |
| WO2021258348A1 (en) * | 2020-06-24 | 2021-12-30 | 深圳市欢太科技有限公司 | Abnormal flow detection method and system and computer storage medium |
| CN113259332A (en) * | 2021-04-29 | 2021-08-13 | 上海电力大学 | Multi-type network flow abnormity detection method and system based on end-to-end |
| CN113625681A (en) * | 2021-07-19 | 2021-11-09 | 湖南大学 | CAN bus abnormality detection method, system and storage medium |
| CN113746862A (en) * | 2021-09-14 | 2021-12-03 | 恒安嘉新（北京）科技股份公司 | Abnormal flow detection method, device and equipment based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 吴晓平;周舟;李洪成;: "Spark框架下基于无指导学习环境的网络流量异常检测研究与实现", 信息网络安全, no. 06, 10 June 2016 (2016-06-10) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110658807A (en) | Vehicle fault diagnosis method, device and system | |
| CN1606760A (en) | Method and device for a vehicle-related telematics service | |
| CN109861882A (en) | The method, apparatus and car-mounted terminal of vehicle bus protocol identification | |
| CN113824684A (en) | Vehicle-mounted network intrusion detection method and system based on transfer learning | |
| CN110933091A (en) | Block chain communication node verification method and device and electronic equipment | |
| CN111490980A (en) | Industrial internet data transmission encryption method | |
| CN111147448A (en) | CAN bus flood attack defense system and method | |
| CN114157469B (en) | Vehicle-mounted network variant attack intrusion detection method based on domain antagonism neural network | |
| CN113723338A (en) | Sensor abnormality detection method, sensor abnormality detection device, and computer-readable storage medium | |
| Boumiza et al. | An anomaly detector for CAN bus networks in autonomous cars based on neural networks | |
| KR102036024B1 (en) | Method and system for vehicle security | |
| Hu et al. | Multi-attack and multi-classification intrusion detection for vehicle-mounted networks based on mosaic-coded convolutional neural network | |
| CN114900331A (en) | Vehicle-mounted CAN bus intrusion detection method based on CAN message characteristics | |
| CN114612011A (en) | Risk prevention and control decision method and device | |
| CN115016433A (en) | Vehicle-mounted CAN bus flow abnormity detection method and system | |
| US20210067970A1 (en) | Distance-based packet filtering method and system thereof | |
| CN111597411A (en) | Method and system for distinguishing and identifying power protocol data frames | |
| CN112464295A (en) | Communication maintenance safety device based on electric power edge gateway equipment | |
| Deng et al. | A lightweight sender identification scheme based on vehicle physical layer characteristics | |
| Xun et al. | An experimental study towards the in-vehicle network of intelligent and connected vehicles | |
| CN116312513A (en) | Intelligent voice control system | |
| CN115866289A (en) | Engineering data integration management system | |
| CN116150603A (en) | Complex modulation mode identification method based on multi-scale feature fusion | |
| CN116567719B (en) | Data transmission method, vehicle-mounted system, device and storage medium | |
| CN113115268B (en) | Method and device for obtaining maximum throughput of Internet of vehicles based on multiple road side units |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |