阅读说明：本技术 一种基于动态信誉值的车联网伪节点检测方法及系统 (Method and system for detecting pseudo nodes of Internet of vehicles based on dynamic credit values ) 是由 谢鹏寿 麻国强 王鑫 王玺强 张新宇 杨昊煊 王靓轩 冯涛 晏燕 于 2020-11-19 设计创作，主要内容包括：本发明涉及一种基于动态信誉值的车联网伪节点检测方法及系统。该方法包括：构建车联网伪节点检测模型；接收车联网内任一车辆节点发送的交通信息；基于所述交通信息,根据所述车联网伪节点检测模型更新所述车辆节点的节点信誉值,确定更新后的节点信誉值；判断所述更新后的节点信誉值是否大于节点信誉值阈值,若是,确定所述车辆节点为合法节点；若否,确定所述车辆节点为伪节点。本发明能够缩短检测效率以及提高伪节点检测准确性。(The invention relates to a method and a system for detecting a pseudo node of a vehicle networking based on a dynamic credit value. The method comprises the following steps: constructing a pseudo node detection model of the Internet of vehicles; receiving traffic information sent by any vehicle node in the Internet of vehicles; based on the traffic information, updating the node credit value of the vehicle node according to the vehicle networking pseudo node detection model, and determining the updated node credit value; judging whether the updated node credit value is larger than a node credit value threshold value or not, and if so, determining that the vehicle node is a legal node; if not, determining that the vehicle node is a pseudo node. The invention can shorten the detection efficiency and improve the detection accuracy of the pseudo node.)

1. A method for detecting a pseudo node in the Internet of vehicles based on a dynamic reputation value is characterized by comprising the following steps:

constructing a pseudo node detection model of the Internet of vehicles; the Internet of vehicles pseudo node detection model comprises a certificate authority, basic equipment fixed on a roadside and a vehicle-mounted bill equipped on a vehicle; the certificate authority is used for being responsible for distributing and canceling communication digital certificates, the basic equipment is used for being responsible for issuing normal traffic information to vehicles within the communication range of the basic equipment, and the vehicle-mounted unit is used for being responsible for issuing, forwarding and receiving the traffic information;

receiving traffic information sent by any vehicle node in the Internet of vehicles; the traffic information comprises the identity type, the driving direction, the driving speed, the acceleration, the timestamp of the transmitted traffic information and the traffic information type of the sender;

based on the traffic information, updating the node credit value of the vehicle node according to the vehicle networking pseudo node detection model, and determining the updated node credit value;

judging whether the updated node credit value is larger than a node credit value threshold value or not to obtain a first judgment result;

if the first judgment result shows that the updated node credit value is larger than the node credit value threshold value, determining that the vehicle node is a legal node;

and if the first judgment result shows that the updated node credit value is not greater than the node credit value threshold value, determining that the vehicle node is a pseudo node.

2. The method for detecting a pseudo node in the internet of vehicles based on a dynamic reputation value according to claim 1, wherein the updating the node reputation value of the vehicle node according to the model for detecting a pseudo node in the internet of vehicles based on the traffic information and determining the updated node reputation value specifically comprises:

verifying whether the sender of the traffic information is the basic equipment or not based on the Internet of vehicles pseudo node detection model to obtain a second judgment result;

if the second judgment result indicates that the sender of the traffic information is the basic equipment, determining the traffic information as training traffic information;

if the second judgment result shows that the sender of the traffic information is not the basic equipment, determining the traffic information as traffic information to be detected;

detecting whether the traffic information to be detected is abnormal traffic information or not based on the Internet of vehicles pseudo node detection model to obtain a third judgment result;

if the third judgment result indicates that the traffic information to be detected is abnormal traffic information, discarding the traffic information to be detected;

if the third judgment result indicates that the traffic information to be detected is normal traffic information, receiving the traffic information to be detected based on the vehicle-mounted unit;

receiving feedback information sent by the vehicle node corresponding to the traffic information to be detected to the certificate authority;

and dynamically updating the node credit value of the vehicle node sending the traffic information to be detected by the certificate authority, and determining the updated node credit value.

3. The method for detecting a pseudo node in the internet of vehicles based on a dynamic reputation value according to claim 2, wherein the method for detecting a pseudo node in the internet of vehicles based on the model for detecting a pseudo node in the internet of vehicles verifies whether the sender of the traffic information is the base device, and obtains a second determination result, and before the method further comprises:

the vehicle node sending the traffic information applies for a communication data certificate to the certificate authority according to the unique identity of the vehicle node sending the traffic information; and issuing a communication digital certificate to the vehicle node sending the traffic information by the certificate authority; the communication digital certificate is used as an identifier that a vehicle node sending the traffic information has communication authority in a network.

4. The method for detecting the pseudo node in the internet of vehicles based on the dynamic reputation value according to claim 2, wherein the detecting whether the traffic information to be detected is abnormal traffic information based on the model for detecting the pseudo node in the internet of vehicles to obtain a third determination result specifically comprises:

classifying the traffic information to be detected by utilizing a support vector machine algorithm based on the Internet of vehicles pseudo node detection model, and determining a classification result consisting of binary 0 and binary 1; the classification result comprises normal traffic information and abnormal traffic information, wherein the normal traffic information is 0, and the abnormal traffic information is 1;

detecting whether the traffic information to be detected is abnormal traffic information according to the classification result to obtain a third judgment result; and the third judgment result is that the traffic information to be detected is abnormal traffic information or the traffic information to be detected is normal traffic information.

5. The method for detecting pseudo nodes in the internet of vehicles based on a dynamic reputation value according to claim 4, wherein the certificate authority dynamically updates the node reputation value of the vehicle node that sends the traffic information to be detected, and determines the updated node reputation value, specifically comprising:

the certificate authority generates a trust vector table based on binary number according to the feedback information; the trust vector table records the classification result of the traffic message issued or forwarded by each vehicle node;

obtaining the attenuation degree of each bit in the binary effective bits in the trust vector table; one effective bit represents the Boolean type judgment of the traffic information issued or forwarded by the vehicle node which receives the traffic information;

and dynamically updating the node credit value of the vehicle node sending the traffic information to be detected according to the attenuation degree, and determining the updated node credit value.

6. A pseudo-node detection system of car networking based on dynamic reputation value, characterized by comprising:

the vehicle networking pseudo node detection model building module is used for building a vehicle networking pseudo node detection model; the Internet of vehicles pseudo node detection model comprises a certificate authority, basic equipment fixed on a roadside and a vehicle-mounted bill equipped on a vehicle; the certificate authority is used for being responsible for distributing and canceling communication digital certificates, the basic equipment is used for being responsible for issuing normal traffic information to vehicles within the communication range of the basic equipment, and the vehicle-mounted unit is used for being responsible for issuing, forwarding and receiving the traffic information;

the traffic information receiving module is used for receiving traffic information sent by any vehicle node in the Internet of vehicles; the traffic information comprises the identity type, the driving direction, the driving speed, the acceleration, the timestamp of the transmitted traffic information and the traffic information type of the sender;

the node credit value updating module is used for updating the node credit value of the vehicle node according to the vehicle networking pseudo node detection model based on the traffic information and determining the updated node credit value;

the first judgment module is used for judging whether the updated node credit value is greater than a node credit value threshold value or not to obtain a first judgment result;

a legal node determining module, configured to determine that the vehicle node is a legal node if the first determination result indicates that the updated node reputation value is greater than a node reputation value threshold;

and the pseudo node determining module is used for determining the vehicle node as a pseudo node if the first judgment result shows that the updated node credit value is not greater than the node credit value threshold.

7. The system for detecting pseudo nodes in the internet of vehicles based on dynamic reputation values according to claim 6, wherein the node reputation value updating module specifically comprises:

the second judgment unit is used for verifying whether the sender of the traffic information is the basic equipment or not based on the Internet of vehicles pseudo node detection model to obtain a second judgment result;

a training traffic information determining unit configured to determine the traffic information as training traffic information if the second determination result indicates that the sender of the traffic information is the basic device;

a traffic information to be detected determining unit, configured to determine the traffic information as traffic information to be detected if the second determination result indicates that the sender of the traffic information is not the basic device;

the third judging unit is used for detecting whether the traffic information to be detected is abnormal traffic information or not based on the Internet of vehicles pseudo node detection model to obtain a third judging result;

a traffic information discarding unit to be detected, configured to discard the traffic information to be detected if the third determination result indicates that the traffic information to be detected is abnormal traffic information;

the traffic information receiving unit to be detected is used for receiving the traffic information to be detected based on the vehicle-mounted unit if the third judgment result shows that the traffic information to be detected is normal traffic information;

the feedback information sending unit is used for receiving the feedback information sent by the vehicle node corresponding to the traffic information to be detected to the certificate authority;

and the node credit value updating unit is used for dynamically updating the node credit value of the vehicle node sending the traffic information to be detected by the certificate authority and determining the updated node credit value.

8. The dynamic reputation value-based Internet of vehicles pseudo-node detection system of claim 7, further comprising:

the communication data certificate application unit is used for applying a communication data certificate to the certificate authority by the vehicle node sending the traffic information according to the unique identity of the vehicle node sending the traffic information; and issuing a communication digital certificate to the vehicle node sending the traffic information by the certificate authority; the communication digital certificate is used as an identifier that a vehicle node sending the traffic information has communication authority in a network.

9. The system for detecting a pseudo node in a vehicle networking based on a dynamic reputation value according to claim 7, wherein the third determining unit specifically comprises:

the classification result determining subunit is used for classifying the traffic information to be detected by utilizing a support vector machine algorithm based on the Internet of vehicles pseudo node detection model and determining a classification result consisting of binary 0 and binary 1; the classification result comprises normal traffic information and abnormal traffic information, wherein the normal traffic information is 0, and the abnormal traffic information is 1;

a third judgment result determining subunit, configured to detect whether the traffic information to be detected is abnormal traffic information according to the classification result, and obtain a third judgment result; and the third judgment result is that the traffic information to be detected is abnormal traffic information or the traffic information to be detected is normal traffic information.

10. The system for detecting a pseudo node in a vehicle networking based on a dynamic reputation value according to claim 9, wherein the node reputation value updating unit specifically comprises:

a trust vector table generating subunit, configured to generate, by the certificate authority, a trust vector table based on a binary number according to the feedback information; the trust vector table records the classification result of the traffic message issued or forwarded by each vehicle node;

an attenuation degree obtaining subunit, configured to obtain an attenuation degree of each bit in a binary significant bit in the trust vector table; one effective bit represents the Boolean type judgment of the traffic information issued or forwarded by the vehicle node which receives the traffic information;

and the node credit value updating subunit is used for dynamically updating the node credit value of the vehicle node sending the traffic information to be detected according to the attenuation degree and determining the updated node credit value.

Technical Field

The invention relates to the field of Internet of vehicles (IoV) safety, in particular to a method and a system for detecting a pseudo node of the Internet of vehicles based on a dynamic credit value.

Background

In the Internet of vehicles, the efficient pseudo node detection technology can effectively increase the research on the safety technology of the Internet of vehicles and can bring satisfaction to the life of people. The technology for detecting the vehicle networking pseudo nodes refers to the fact that some vehicle nodes with malicious attack behaviors are detected and removed through a certain algorithm in a vehicle networking environment, and therefore safe communication among nodes in a network can be guaranteed. Based on an authentication mechanism and a trust model, a dynamic trust model based on node information and behaviors is designed, trust evaluation with strong real-time performance and high accuracy is provided, and method support is provided for actively sensing malicious nodes; researchers analyze and summarize the position and the role of the global measurement in the network system security, summarize and summarize 3 development stages (perception, cognition and deepening) of the measurement and the characteristics thereof, give the working process of the global measurement, comb methods such as a measurement model, a measurement system, a measurement tool and the like, and point out the respective characteristics and the role and the mutual relation thereof in the security measurement. Although the detection algorithm solves the problems that a single authentication mechanism and a trust model cannot meet the safety differentiation guarantee under the complex and multi-communication scene of the vehicle networking, most of the detection algorithms are developed aiming at the Sybil attack resistance behavior of the legal nodes, so that the vehicle pseudo nodes in the vehicle network cannot be quickly identified, and the pseudo node detection time is long and the detection efficiency is low.

Disclosure of Invention

The invention aims to provide a method and a system for detecting a pseudo node of a vehicle networking based on a dynamic credit value, and aims to solve the problems of long detection time and low detection efficiency of the pseudo node of the vehicle networking.

In order to achieve the purpose, the invention provides the following scheme:

a method for detecting a pseudo node in the Internet of vehicles based on a dynamic reputation value comprises the following steps:

constructing a pseudo node detection model of the Internet of vehicles; the Internet of vehicles pseudo node detection model comprises a certificate authority, basic equipment fixed on a roadside and a vehicle-mounted bill equipped on a vehicle; the certificate authority is used for being responsible for distributing and canceling communication digital certificates, the basic equipment is used for being responsible for issuing normal traffic information to vehicles within the communication range of the basic equipment, and the vehicle-mounted unit is used for being responsible for issuing, forwarding and receiving the traffic information;

receiving traffic information sent by any vehicle node in the Internet of vehicles; the traffic information comprises the identity type, the driving direction, the driving speed, the acceleration, the timestamp of the transmitted traffic information and the traffic information type of the sender;

based on the traffic information, updating the node credit value of the vehicle node according to the vehicle networking pseudo node detection model, and determining the updated node credit value;

judging whether the updated node credit value is larger than a node credit value threshold value or not to obtain a first judgment result;

if the first judgment result shows that the updated node credit value is larger than the node credit value threshold value, determining that the vehicle node is a legal node;

and if the first judgment result shows that the updated node credit value is not greater than the node credit value threshold value, determining that the vehicle node is a pseudo node.

Optionally, the updating, based on the traffic information, the node reputation value of the vehicle node according to the vehicle networking pseudo node detection model, and determining the updated node reputation value specifically include:

verifying whether the sender of the traffic information is the basic equipment or not based on the Internet of vehicles pseudo node detection model to obtain a second judgment result;

if the second judgment result indicates that the sender of the traffic information is the basic equipment, determining the traffic information as training traffic information;

if the second judgment result shows that the sender of the traffic information is not the basic equipment, determining the traffic information as traffic information to be detected;

detecting whether the traffic information to be detected is abnormal traffic information or not based on the Internet of vehicles pseudo node detection model to obtain a third judgment result;

if the third judgment result indicates that the traffic information to be detected is abnormal traffic information, discarding the traffic information to be detected;

if the third judgment result indicates that the traffic information to be detected is normal traffic information, receiving the traffic information to be detected based on the vehicle-mounted unit;

receiving feedback information sent by the vehicle node corresponding to the traffic information to be detected to the certificate authority;

and dynamically updating the node credit value of the vehicle node sending the traffic information to be detected by the certificate authority, and determining the updated node credit value.

Optionally, the verifying whether the sender of the traffic information is the basic device based on the vehicle networking pseudo node detection model to obtain a second determination result further includes:

the vehicle node sending the traffic information applies for a communication data certificate to the certificate authority according to the unique identity of the vehicle node sending the traffic information; and issuing a communication digital certificate to the vehicle node sending the traffic information by the certificate authority; the communication digital certificate is used as an identifier that a vehicle node sending the traffic information has communication authority in a network.

Optionally, the detecting, based on the internet of vehicles pseudo node detection model, whether the traffic information to be detected is abnormal traffic information to obtain a third determination result, which specifically includes:

classifying the traffic information to be detected by utilizing a support vector machine algorithm based on the Internet of vehicles pseudo node detection model, and determining a classification result consisting of binary 0 and binary 1; the classification result comprises normal traffic information and abnormal traffic information, wherein the normal traffic information is 0, and the abnormal traffic information is 1;

detecting whether the traffic information to be detected is abnormal traffic information according to the classification result to obtain a third judgment result; and the third judgment result is that the traffic information to be detected is abnormal traffic information or the traffic information to be detected is normal traffic information.

Optionally, the dynamically updating, by the certificate authority, the node reputation value of the vehicle node that sends the traffic information to be detected, and determining the updated node reputation value specifically include:

the certificate authority generates a trust vector table based on binary number according to the feedback information; the trust vector table records the classification result of the traffic message issued or forwarded by each vehicle node;

obtaining the attenuation degree of each bit in the binary effective bits in the trust vector table; one effective bit represents the Boolean type judgment of the traffic information issued or forwarded by the vehicle node which receives the traffic information;

and dynamically updating the node credit value of the vehicle node sending the traffic information to be detected according to the attenuation degree, and determining the updated node credit value.

A pseudo-node detection system of a vehicle networking based on a dynamic reputation value, comprising:

the vehicle networking pseudo node detection model building module is used for building a vehicle networking pseudo node detection model; the Internet of vehicles pseudo node detection model comprises a certificate authority, basic equipment fixed on a roadside and a vehicle-mounted bill equipped on a vehicle; the certificate authority is used for being responsible for distributing and canceling communication digital certificates, the basic equipment is used for being responsible for issuing normal traffic information to vehicles within the communication range of the basic equipment, and the vehicle-mounted unit is used for being responsible for issuing, forwarding and receiving the traffic information;

the traffic information receiving module is used for receiving traffic information sent by any vehicle node in the Internet of vehicles; the traffic information comprises the identity type, the driving direction, the driving speed, the acceleration, the timestamp of the transmitted traffic information and the traffic information type of the sender;

the node credit value updating module is used for updating the node credit value of the vehicle node according to the vehicle networking pseudo node detection model based on the traffic information and determining the updated node credit value;

the first judgment module is used for judging whether the updated node credit value is greater than a node credit value threshold value or not to obtain a first judgment result;

a legal node determining module, configured to determine that the vehicle node is a legal node if the first determination result indicates that the updated node reputation value is greater than a node reputation value threshold;

and the pseudo node determining module is used for determining the vehicle node as a pseudo node if the first judgment result shows that the updated node credit value is not greater than the node credit value threshold.

Optionally, the node reputation value updating module specifically includes:

the second judgment unit is used for verifying whether the sender of the traffic information is the basic equipment or not based on the Internet of vehicles pseudo node detection model to obtain a second judgment result;

a training traffic information determining unit configured to determine the traffic information as training traffic information if the second determination result indicates that the sender of the traffic information is the basic device;

a traffic information to be detected determining unit, configured to determine the traffic information as traffic information to be detected if the second determination result indicates that the sender of the traffic information is not the basic device;

the third judging unit is used for detecting whether the traffic information to be detected is abnormal traffic information or not based on the Internet of vehicles pseudo node detection model to obtain a third judging result;

a traffic information discarding unit to be detected, configured to discard the traffic information to be detected if the third determination result indicates that the traffic information to be detected is abnormal traffic information;

the traffic information receiving unit to be detected is used for receiving the traffic information to be detected based on the vehicle-mounted unit if the third judgment result shows that the traffic information to be detected is normal traffic information;

the feedback information sending unit is used for receiving the feedback information sent by the vehicle node corresponding to the traffic information to be detected to the certificate authority;

and the node credit value updating unit is used for dynamically updating the node credit value of the vehicle node sending the traffic information to be detected by the certificate authority and determining the updated node credit value.

Optionally, the method further includes:

the communication data certificate application unit is used for applying a communication data certificate to the certificate authority by the vehicle node sending the traffic information according to the unique identity of the vehicle node sending the traffic information; and issuing a communication digital certificate to the vehicle node sending the traffic information by the certificate authority; the communication digital certificate is used as an identifier that a vehicle node sending the traffic information has communication authority in a network.

Optionally, the third determining unit specifically includes:

the classification result determining subunit is used for classifying the traffic information to be detected by utilizing a support vector machine algorithm based on the Internet of vehicles pseudo node detection model and determining a classification result consisting of binary 0 and binary 1; the classification result comprises normal traffic information and abnormal traffic information, wherein the normal traffic information is 0, and the abnormal traffic information is 1;

a third judgment result determining subunit, configured to detect whether the traffic information to be detected is abnormal traffic information according to the classification result, and obtain a third judgment result; and the third judgment result is that the traffic information to be detected is abnormal traffic information or the traffic information to be detected is normal traffic information.

Optionally, the node reputation value updating unit specifically includes:

a trust vector table generating subunit, configured to generate, by the certificate authority, a trust vector table based on a binary number according to the feedback information; the trust vector table records the classification result of the traffic message issued or forwarded by each vehicle node;

an attenuation degree obtaining subunit, configured to obtain an attenuation degree of each bit in a binary significant bit in the trust vector table; one effective bit represents the Boolean type judgment of the traffic information issued or forwarded by the vehicle node which receives the traffic information;

and the node credit value updating subunit is used for dynamically updating the node credit value of the vehicle node sending the traffic information to be detected according to the attenuation degree and determining the updated node credit value.

According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the invention provides a method and a system for detecting a pseudo node of a vehicle networking based on a dynamic credit value.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.

FIG. 1 is a flow chart of a method for detecting pseudo nodes in a vehicle networking system based on dynamic reputation values, which is provided by the present invention;

FIG. 2 is a model diagram of the Internet of vehicles pseudo node detection of the present invention;

FIG. 3 is a diagram of traffic information preprocessing of the present invention;

FIG. 4 is a diagram of the SVM classification process of the present invention;

FIG. 5 is a diagram of a pseudo node detection system of the Internet of vehicles based on dynamic reputation values according to the present invention;

FIG. 6 is another pseudo node detection flow chart provided by the present invention;

FIG. 7 is a comparison graph of node reputation values of the present invention;

FIG. 8 is a diagram illustrating the variation of the quasi-inspection rate with the number of traffic messages according to the present invention;

FIG. 9 is a diagram illustrating the detection overhead of the present invention as a function of the number of traffic messages.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The invention aims to provide a method and a system for detecting a pseudo node of a vehicle networking based on a dynamic credit value, which can shorten the detection efficiency and improve the detection accuracy of the pseudo node.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

For clarity of explanation, the following definitions are made:

definition 1: traffic information category set E ═ (E)₁，e₂，e₃，…，e_n)，e_iSome specific traffic information, such as emergency brake information (EEBL) of a vehicle, traffic accident notification information (PCN), road congestion notification information (RCN), etc., is issued or forwarded on behalf of each node.

Definition 2: traffic information in the internet of vehicles can be divided into two categories Θ {0, 1}, where "0" represents normal traffic information and "1" represents abnormal traffic information. The normal traffic information refers to the guiding traffic information issued or forwarded by the legal node, and the abnormal traffic information refers to the malicious traffic information which is forged, tampered, distributed or forwarded by the pseudo node. Here, it is assumed that the traffic information issued by the RSU is normally authentic.

Definition 3: vehicle node set V ═ V (V)₁，v₂，…，v_n) In the process of driving, vehicle nodes in the internet of vehicles broadcast traffic information attached with digital signatures and public key certificates to other surrounding vehicle nodes.

Since the characteristics of the traffic information in the internet of vehicles have multiple dimensions, we can express effective characteristics (EF) in the traffic information in the form of column vectors, that is, EF ═ x₁；x₂；x₃；…；x_n]Then its corresponding Data Set (DS) can be expressed as DS { (x)₁，y₁)，(x₂，y₂)，…，(x_n，y_n) In which y is_iE Θ represents the valid feature x for_iN is the number of valid features. Table 1 shows the effective characteristics of traffic information, and Table 1 showsThe effective features in the traffic information are shown, and the symbols in the brackets are short for the effective features.

TABLE 1

Fig. 1 is a flowchart of a method for detecting a pseudo node in a vehicle networking based on a dynamic reputation value, and as shown in fig. 1, the method for detecting a pseudo node in a vehicle networking based on a dynamic reputation value includes:

step 101: constructing a pseudo node detection model of the Internet of vehicles; the Internet of vehicles pseudo node detection model comprises a certificate authority, basic equipment fixed on a roadside and a vehicle-mounted bill equipped on a vehicle; the certificate authority is used for being responsible for distributing and canceling communication digital certificates, the basic device is used for being responsible for issuing normal traffic information to vehicles within the communication range of the basic device, and the vehicle-mounted unit is used for being responsible for issuing, forwarding and receiving the traffic information.

Fig. 2 is a diagram of a detection model of a pseudo node in the internet of vehicles, and as shown in fig. 2, a detection model of a pseudo node in the internet of vehicles is constructed. The model mainly comprises 3 entities: certificate Authorities (CAs), Road Side Units (RSUs), and onboard units (OBUs) equipped on vehicles. The CA is responsible for distributing and revoking the certificate; the RSU is responsible for issuing normal and credible traffic messages to vehicles within the communication range of the RSU; the OBU is responsible for issuing, forwarding and receiving traffic messages, communicating by means of vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I).

Considering the non-repudiation of traffic messages in the security requirements of the internet of vehicles, the effective characteristics of traffic messages, and the dynamics of the internet of vehicles, the communication message format is designed as follows.

The communication messages between nodes are defined as follows:

Msg₁(Node_Id_i,msgContent_1i)

wherein Node _ Id_iUnique identity ID, msgContent, representing a node issuing or forwarding a traffic message_1iRepresenting traffic messages sent by the node.

The communication messages sent by the RSU to the node are defined as follows:

Msg₂(Rsu_Id_i,msgContent_2i)

wherein Rsu _ Id_iRSU unique identity ID, msgContent, representing transmitted traffic messages_2iRepresenting traffic messages sent by the RSU.

The feedback message sent by the node to the CA is defined as follows:

Msg₃(Node_Id_j,Node_Id_i,msgType)

wherein Node _ Id_jIndicating the Node-unique identity ID, Node _ Id, receiving the traffic message_iThe unique ID of the node for issuing or forwarding the traffic message is shown, the msgType is Boolean type and is used for receiving the node V_jInform CA of node V_iThe traffic message issued or forwarded is either normal (set to 0) or abnormal (set to 1).

Step 102: receiving traffic information sent by any vehicle node in the Internet of vehicles; the traffic information includes an identity type of the sender, a driving direction, a driving speed, an acceleration, a time stamp of the transmitted traffic information, and a traffic information type.

Step 103: and based on the traffic information, updating the node credit value of the vehicle node according to the vehicle networking pseudo node detection model, and determining the updated node credit value.

The step 103 specifically includes: verifying whether the sender of the traffic information is the basic equipment or not based on the Internet of vehicles pseudo node detection model to obtain a second judgment result; if the second judgment result indicates that the sender of the traffic information is the basic equipment, determining the traffic information as training traffic information; if the second judgment result shows that the sender of the traffic information is not the basic equipment, determining the traffic information as traffic information to be detected; detecting whether the traffic information to be detected is abnormal traffic information or not based on the Internet of vehicles pseudo node detection model to obtain a third judgment result; if the third judgment result indicates that the traffic information to be detected is abnormal traffic information, discarding the traffic information to be detected; if the third judgment result indicates that the traffic information to be detected is normal traffic information, receiving the traffic information to be detected based on the vehicle-mounted unit; receiving feedback information sent by the vehicle node corresponding to the traffic information to be detected to the certificate authority; and dynamically updating the node credit value of the vehicle node sending the traffic information to be detected by the certificate authority, and determining the updated node credit value.

The verifying whether the sender of the traffic information is the basic device based on the vehicle networking pseudo node detection model to obtain a second judgment result, wherein the method comprises the following steps: the vehicle node sending the traffic information applies for a communication data certificate to the certificate authority according to the unique identity of the vehicle node sending the traffic information; and issuing a communication digital certificate to the vehicle node sending the traffic information by the certificate authority; the communication digital certificate is used as an identifier that a vehicle node sending the traffic information has communication authority in a network.

The detecting whether the traffic information to be detected is abnormal traffic information based on the internet of vehicles pseudo node detection model to obtain a third judgment result, specifically comprising:

classifying the traffic information to be detected by utilizing a support vector machine algorithm based on the Internet of vehicles pseudo node detection model, and determining a classification result consisting of binary 0 and binary 1; the classification result comprises normal traffic information and abnormal traffic information, wherein the normal traffic information is 0, and the abnormal traffic information is 1;

detecting whether the traffic information to be detected is abnormal traffic information according to the classification result to obtain a third judgment result; and the third judgment result is that the traffic information to be detected is abnormal traffic information or the traffic information to be detected is normal traffic information.

The dynamically updating, by the certificate authority, the node reputation value of the vehicle node that sends the traffic information to be detected, and determining the updated node reputation value specifically include: the certificate authority generates a trust vector table based on binary number according to the feedback information; the trust vector table records the classification result of the traffic message issued or forwarded by each vehicle node; obtaining the attenuation degree of each bit in the binary effective bits in the trust vector table; one effective bit represents the Boolean type judgment of the traffic information issued or forwarded by the vehicle node which receives the traffic information; and dynamically updating the node credit value of the vehicle node sending the traffic information to be detected according to the attenuation degree, and determining the updated node credit value.

Step 104: and judging whether the updated node reputation value is greater than a node reputation value threshold value, if so, executing step 105, and if not, executing step 106.

Step 105: and if the first judgment result shows that the updated node credit value is greater than the node credit value threshold, determining that the vehicle node is a legal node.

Step 106: and if the first judgment result shows that the updated node credit value is not greater than the node credit value threshold value, determining that the vehicle node is a pseudo node.

Based on the above pseudo node detection model of the internet of vehicles, the specific operation process in practical application is as follows:

node V_iApplies for a certificate to the CA. Node V_iApplying a digital certificate to a CA according to a unique identity ID of the CA to obtain communication and legal authority with other nodes in a network;

CA to V_iA certificate is issued. Node V_iThe digital certificate is used as an identifier which has communication authority in a network;

and sending the traffic message. Node V_iTo node V_jTransmitting traffic message msgContent_1iWhile RSU is directed to node V_jTransmitting traffic message msgContent_2i；

Traffic messages are detected. Node V_jReceiving node V_iAfter the traffic message, the node V is sent according to the reliable traffic message sent by the RSU_iThe transmitted message is detected to determine whether it is abnormal.

Feeding back to the CA. Node V_jCompleting node V locally_iAfter detecting the issued or forwarded traffic message, if the traffic message is normal, selecting to receive; otherwise, it is directly discarded. At the same time, node V_jSending a feedback message Msg₃To the certification authority CA.

The CA updates the node reputation value. Authentication center CA according to node V_jFeedback message pair node V_iDynamically updates the credit value of the node and judges the node V_iWhether it is a dummy node.

To sum up, the pseudo node detection algorithm provided by the invention mainly comprises three parts, namely traffic message preprocessing, traffic message anomaly detection and node reputation value dynamic updating:

preprocessing traffic messages:

fig. 3 is a diagram of traffic information preprocessing of the present invention, as shown in fig. 3, in order to avoid unnecessary computational overhead. The traffic message is preprocessed mainly from the three aspects of digital signature, timeliness verification and identity type verification. First, the recipient verifies the integrity and non-repudiation of the traffic message by verifying the digital signature; then, verifying timeliness by adopting a batch authentication method, if the traffic message exceeds the time effective range, the traffic message is invalid, and the traffic message can be ignored; and finally, taking the traffic message sent by the RSU as a training message, and taking the traffic message issued or forwarded by the vehicle node as a message to be detected. The time validity of a traffic message is expressed as formula (1):

t-t₀＜Δt (1)

wherein t represents the time when the node receives the traffic message, t₀A delta t table representing the time of distribution or forwarding of the traffic informationThe validity period of the traffic message is shown.

Traffic message detection:

at present, in the research field of intrusion detection algorithms, the algorithms mainly adopted include Support Vector Machines (SVMs), clustering, association rules, deep learning, decision trees and the like, and the SVMs are selected to realize classification detection of the traffic messages of the internet of vehicles.

Fig. 4 is a diagram of an SVM classification process of the present invention, as shown in fig. 4, first extracting an effective feature vector EF of a multidimensional traffic message according to formula 2, wherein:

the effective feature vector EF of the internet of vehicles multi-dimensional traffic message can be expressed as formula (2).

EF＝[e；d；v；a；t₀；s] (2)

Wherein e, d, v, a, t₀And s represents a valid feature in the traffic information, and the meaning thereof is shown in the foregoing table 1.

And establishing an optimal classification hyperplane by means of an SVM algorithm, so that the distance between two types of samples on two sides of the plane, which are closest to the plane, is maximized. For a multi-dimensional sample set, the system randomly generates a hyperplane and continuously moves, samples are classified until sample points belonging to different classes in training samples are just positioned on two sides of the hyperplane, a plurality of hyperplanes meeting the condition are possible, and the SVM finds the hyperplane under the condition of ensuring the classification accuracy, so that blank areas on two sides of the hyperplane are maximized, and the optimal classification of separable samples is realized. In the invention, the distance D (x) from the sample point to the classification hyperplane is calculated by adopting a formula 3, and an optimal classification hyperplane can be determined by using a formula 4.

The SVM decision function is shown in equation (3).

Wherein the content of the first and second substances,is a training messageValid feature x_iThe corresponding lagrange factor, K (·) is the kernel function and θ is the offset.

The optimal classification hyperplane is shown in equation (4).

Wherein epsilon_iThe number of the effective features of the traffic message is n.

The traffic message sample is divided into two sides of the plane through an optimal classification hyperplane, the two sides are respectively represented by 1 (abnormal) and 0 (normal), the authentication center CA is responsible for maintaining the number of 1 and 0, a set containing a plurality of 0 s and 1 s can be obtained when a plurality of traffic messages are sent by vehicle nodes in a period of time, then a calculation formula 6 is constructed, the weight occupied by each bit in the set is calculated, and finally RV (i) is comprehensively calculated through a formula 7 and is used as the credit value of the node.

Therefore, the characteristics of the Internet of vehicles are considered, the two existing reputation value calculation methods are combined, and a new node reputation value calculation and updating method is designed by introducing attenuation weight.

And (3) updating the node reputation value:

the attenuation weight g (k) represents the attenuation degree of each bit in the binary effective bits in the trust vector table, one effective bit represents the Boolean type judgment of the node j on the traffic message issued or forwarded by the node i, 1 and 0 respectively represent the abnormal traffic message and the normal traffic message, and the satisfied conditions are shown in formula (5).

Where m is the number of traffic messages communicated between nodes, 0< g (k-1) < g (k) < 1.

Since the last calculated node reputation value should be attenuated to different degrees depending on the traffic message detection time, the condition that the attenuation weight of the k-th bit on the valid bit should satisfy is as shown in equation (6).

Wherein, t_tIs the current time, t_kIs the time that the node j judges the kth traffic message sent by the node i, and A is a proportionality coefficient.

Therefore, the calculation of the overall reputation value rv (i) of the node i by CA can be expressed as shown in equation (7).

Fig. 5 is a structural diagram of a pseudo node detection system of a vehicle networking based on a dynamic reputation value, and as shown in fig. 5, a pseudo node detection system of a vehicle networking based on a dynamic reputation value includes:

the vehicle networking pseudo node detection model building module 501 is used for building a vehicle networking pseudo node detection model; the Internet of vehicles pseudo node detection model comprises a certificate authority, basic equipment fixed on a roadside and a vehicle-mounted bill equipped on a vehicle; the certificate authority is used for being responsible for distributing and canceling communication digital certificates, the basic device is used for being responsible for issuing normal traffic information to vehicles within the communication range of the basic device, and the vehicle-mounted unit is used for being responsible for issuing, forwarding and receiving the traffic information.

A traffic information receiving module 502, configured to receive traffic information sent by any vehicle node in the internet of vehicles; the traffic information includes an identity type of the sender, a driving direction, a driving speed, an acceleration, a time stamp of the transmitted traffic information, and a traffic information type.

And a node reputation value updating module 503, configured to update the node reputation value of the vehicle node according to the vehicle networking pseudo node detection model based on the traffic information, and determine an updated node reputation value.

The node reputation value updating module 503 specifically includes: the second judgment unit is used for verifying whether the sender of the traffic information is the basic equipment or not based on the Internet of vehicles pseudo node detection model to obtain a second judgment result; a training traffic information determining unit configured to determine the traffic information as training traffic information if the second determination result indicates that the sender of the traffic information is the basic device; a traffic information to be detected determining unit, configured to determine the traffic information as traffic information to be detected if the second determination result indicates that the sender of the traffic information is not the basic device; the third judging unit is used for detecting whether the traffic information to be detected is abnormal traffic information or not based on the Internet of vehicles pseudo node detection model to obtain a third judging result; a traffic information discarding unit to be detected, configured to discard the traffic information to be detected if the third determination result indicates that the traffic information to be detected is abnormal traffic information; the traffic information receiving unit to be detected is used for receiving the traffic information to be detected based on the vehicle-mounted unit if the third judgment result shows that the traffic information to be detected is normal traffic information; the feedback information sending unit is used for receiving the feedback information sent by the vehicle node corresponding to the traffic information to be detected to the certificate authority; and the node credit value updating unit is used for dynamically updating the node credit value of the vehicle node sending the traffic information to be detected by the certificate authority and determining the updated node credit value.

The invention also includes: the communication data certificate application unit is used for applying a communication data certificate to the certificate authority by the vehicle node sending the traffic information according to the unique identity of the vehicle node sending the traffic information; and issuing a communication digital certificate to the vehicle node sending the traffic information by the certificate authority; the communication digital certificate is used as an identifier that a vehicle node sending the traffic information has communication authority in a network.

The third determining unit specifically includes: the classification result determining subunit is used for classifying the traffic information to be detected by utilizing a support vector machine algorithm based on the Internet of vehicles pseudo node detection model and determining a classification result consisting of binary 0 and binary 1; the classification result comprises normal traffic information and abnormal traffic information, wherein the normal traffic information is 0, and the abnormal traffic information is 1; a third judgment result determining subunit, configured to detect whether the traffic information to be detected is abnormal traffic information according to the classification result, and obtain a third judgment result; and the third judgment result is that the traffic information to be detected is abnormal traffic information or the traffic information to be detected is normal traffic information.

The node reputation value updating unit specifically includes: a trust vector table generating subunit, configured to generate, by the certificate authority, a trust vector table based on a binary number according to the feedback information; the trust vector table records the classification result of the traffic message issued or forwarded by each vehicle node; an attenuation degree obtaining subunit, configured to obtain an attenuation degree of each bit in a binary significant bit in the trust vector table; one effective bit represents the Boolean type judgment of the traffic information issued or forwarded by the vehicle node which receives the traffic information; and the node credit value updating subunit is used for dynamically updating the node credit value of the vehicle node sending the traffic information to be detected according to the attenuation degree and determining the updated node credit value.

The first determining module 504 is configured to determine whether the updated node reputation value is greater than a node reputation value threshold, so as to obtain a first determination result.

A legal node determining module 505, configured to determine that the vehicle node is a legal node if the first determination result indicates that the updated node reputation value is greater than the node reputation value threshold.

A pseudo node determining module 506, configured to determine that the vehicle node is a pseudo node if the first determination result indicates that the updated node reputation value is not greater than the node reputation value threshold.

Based on the method and system for detecting pseudo nodes in the internet of vehicles based on the dynamic reputation value, the detection method can be further expressed by the following steps, and fig. 6 is another pseudo node detection flow chart provided by the invention, as shown in fig. 6:

step 1: after receiving the traffic message, the node Vj preprocesses the message by adopting a preprocessing function pre _ Treat (), filters out invalid traffic messages, verifies the identity of a sender, takes the sent traffic message as a training traffic message if the sender s is an RSU, and takes the sent traffic message as a traffic message to be detected if the sender s is a general vehicle node.

Step 2: and (2) transmitting the traffic message to be detected into a check () function, classifying the traffic message according to a formula (3) and a formula (4), namely when D (x) is 0, classifying the traffic message as normal, and setting msgType as 0, otherwise, when D (x) is 1, classifying the traffic message as abnormal, and setting msgType as 1.

And step 3: CA according to node V_jMessage Msg fed back₃The update () function is applied to node V according to equation (7)_iIs dynamically updated, i.e. node V is calculated_iRV (i) of (1).

And 4, step 4: CA makes a decision on the vehicle node according to the function isforgeyNode (), i.e. if RV (i)>M, continuing to monitor the behavior of the mobile terminal; otherwise, judging the node V_iIs a pseudo node and is issued to a node V_iThe certificate of (a) is added to the revocation certificate list.

The main functions involved are:

(1) pre _ Treat (): a pre-processing function.

(2) check (): traffic message detection function.

(3) update (): a reputation value update function.

(4) isforgeynode (): a pseudo node decision function.

Fig. 7 is a comparison diagram of node reputation values, as shown in fig. 7, after message detection, the certificate authority CA will automatically maintain a trust vector table based on binary numbers according to the detection result fed back by the node to record the historical state of each node issuing or forwarding traffic messages. The current credit value calculation method based on binary number has two methods: one is to calculate the reputation value based on a binary system of numbers, and the other is to count the number of 0's or 1's on the valid bit in the trust vector table to calculate the reputation value.

Fig. 8 is a schematic diagram of the variation of the quasi-detection rate of the invention with the number of traffic messages, fig. 9 is a schematic diagram of the variation of the detection overhead of the invention with the number of traffic messages, as shown in fig. 8-9, the invention greatly improves the detection accuracy of the pseudo nodes by classifying with the SVM algorithm, and shortens the detection time.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.

The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.