CN113380024A - Reputation updating method and trust calculation method based on Internet of vehicles - Google Patents
Reputation updating method and trust calculation method based on Internet of vehicles Download PDFInfo
- Publication number
- CN113380024A CN113380024A CN202110582032.7A CN202110582032A CN113380024A CN 113380024 A CN113380024 A CN 113380024A CN 202110582032 A CN202110582032 A CN 202110582032A CN 113380024 A CN113380024 A CN 113380024A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- trust
- vehicles
- reputation
- classification set
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 title claims abstract description 16
- 230000002452 interceptive effect Effects 0.000 claims abstract description 38
- 230000003993 interaction Effects 0.000 claims abstract description 37
- 238000004891 communication Methods 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000010845 search algorithm Methods 0.000 claims description 8
- 230000006855 networking Effects 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 26
- 230000006399 behavior Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000007935 neutral effect Effects 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 235000008694 Humulus lupulus Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 229910052723 transition metal Inorganic materials 0.000 description 1
- 150000003624 transition metals Chemical class 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Mathematical Optimization (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of safety communication in the Internet of vehicles, belongs to the field of trust management of the Internet of vehicles, and particularly relates to a reputation updating method and a trust calculation method based on the Internet of vehicles; the reputation updating method comprises the steps that a road side unit receives interactive information uploaded by different vehicles, verifies the interactive information and stores vehicle information which is verified successfully; classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle entering the vehicle trust management system for the first time exists or not, and dividing the vehicle into a first classification set and a second classification set; and respectively calculating the reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle. The invention can more accurately express the attribute of the vehicle and effectively avoid the problems of single-point fault network congestion and the like.
Description
Technical Field
The invention relates to the field of safety communication in the Internet of vehicles, belongs to the field of trust management of the Internet of vehicles, and particularly relates to a reputation updating method and a trust calculation method based on the Internet of vehicles.
Background
With the vigorous development of technologies such as sensor Networks, wireless access, artificial intelligence and automatic driving, a vehicle dynamic Ad Hoc network (VANET for short) has become a cornerstone of an Intelligent Transportation System (ITS). Vehicles perform Vehicle-to-roadside unit (V2I) Communication and Vehicle-to-Vehicle (V2V) Communication by means of Dedicated Short Range Communication (DSRC), cellular technology, and the like, and form VANET in a certain area. The VANET can serve services such as real-time positioning, streaming media video and accident warning, and the services improve traffic efficiency and road safety and bring better driving experience. However, some malicious vehicles exist in the VANET interaction process, and can create malicious behaviors, which cause communication delay, traffic jam, privacy information leakage and the like, and serious people may threaten the life and property safety of people. Therefore, the security issue has been the focus of VANET research.
In the running process of the VANET, the vehicle decides the next driving scheme according to the received message, and the vehicle judges the credibility of the message by using the reputation value of the message source vehicle. However, due to the high dynamics and behavior variability of vehicles, the management of the reputation database of the vehicle becomes crucial. The storage of the trust database needs to meet the requirements of distribution, non-tampering, consistency, traceability and the like. The key idea of the block chain technology design is to realize data storage and management of a center, the block chain technology is introduced into a vehicle networking trust management system to efficiently manage a vehicle trust database, and the characteristics of the block chain are in accordance with the requirements of vehicle networking trust database management. By using the RSU device as a blockchain network node, the vehicle can upload messages to the RSU and query the RSU for data information required by itself.
The relevant literature currently carries out a lot of research work in applying blockchain to trust management systems for vehicles, but few literature considers how to adapt between the characteristics of blockchain networks and the high requirements of VANET networks for latency. In addition, in an actual VANET scenario, the behavior of the vehicle is variable, and the reputation value of the vehicle should also change, so when calculating the reputation value of the vehicle, the calculated weights for behavior performance of different time periods should be different. Therefore, an accurate reputation value updating algorithm needs to be designed, and distributed storage of the vehicle trust database is performed by reasonably utilizing the block chain technology.
Disclosure of Invention
In order to solve the prior art problems, the invention provides a reputation updating method and a trust degree calculating method based on the Internet of vehicles. In order to adapt the blockchain network to the VANET system, the invention designs a method for periodically updating the reputation value. And when the vehicle requests another vehicle reputation value in real time, a trust path searching algorithm between the two vehicles is designed, and the trust relationship between the two vehicles can be more accurately obtained by combining the reputation value of the vehicle in a period.
In a first aspect of the present invention, the present invention provides a reputation updating method based on internet of vehicles, the method including:
the road side unit receives the interactive information uploaded by different vehicles, verifies the interactive information and stores the vehicle information which is verified successfully;
classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle which enters the vehicle trust management system for the first time is included; acquiring all interactive information of a certain vehicle on a road side unit, taking the vehicle corresponding to the interactive information as a first classification set of the certain vehicle, judging whether the vehicle in the first classification set enters a vehicle trust management system for the first time, and taking the vehicle entering the vehicle trust management system for the first time as a second classification set;
and respectively calculating the reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle.
In a second aspect of the present invention, the present invention provides a trust calculation method based on internet of vehicles, the method comprising:
the road side unit receives the interactive information uploaded by different vehicles, verifies the interactive information and stores the vehicle information which is verified successfully;
classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle which enters the vehicle trust management system for the first time is included; acquiring all interactive information of a certain vehicle on a road side unit, taking the vehicle corresponding to the interactive information as a first classification set of the certain vehicle, judging whether the vehicle in the first classification set enters a vehicle trust management system for the first time, and taking the vehicle entering the vehicle trust management system for the first time as a second classification set;
respectively calculating reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle;
and calculating a trust path between the vehicle and the target vehicle by utilizing a trust path search algorithm based on the reputation value of each vehicle.
The invention has the beneficial effects that:
in the block chain assisted vehicle reputation management system, historical interaction of vehicles is used as a judgment basis, the reputation value of the vehicle is calculated based on a three-value subjective logic algorithm, and the interaction frequency and other factors of the vehicle are considered in combination; dynamic attenuation factors and the like are introduced to quantify the trust relationship between the reputation value of the vehicle and the vehicle, and compared with the traditional reputation updating algorithm, the method can more accurately express the attribute of the vehicle. The trust database is stored in a distributed mode by using a block chain technology, and a block chain network is adapted to a VANET system by using a periodic updating method; compared with the traditional centralized management mode, the method effectively avoids the problems of network congestion caused by single point of failure and the like. The invention also designs a trust path searching algorithm based on depth-first search to obtain the trust path between the two vehicles, and the calculation accuracy is improved by combining a six-degree space separation theory and the like. The invention obviously improves the identification efficiency of the malicious vehicles and shows good anti-attack performance in the face of group series-connection attack and On-off attack.
Drawings
FIG. 1 is a diagram of a system model employed in an embodiment of the present invention;
FIG. 2 is a flowchart of a reputation updating method based on Internet of vehicles according to an embodiment of the present invention;
FIG. 3 is a flow chart of a reputation update algorithm in a preferred embodiment of the present invention;
FIG. 4 is a flowchart of a trust calculation method based on Internet of vehicles according to an embodiment of the present invention;
fig. 5 is a flowchart of a trust path search algorithm according to an embodiment of the present invention.
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.
Fig. 1 is a diagram of a system model used in an embodiment of the present invention, and as shown in fig. 1, the system model is a converged model of a blockchain network and a VANET system, in which a vehicle communicates with the vehicle via a V2V communication link and the vehicle communicates with a roadside unit via a V2I communication link; block chain networks are formed among the RSUs; suppose that the vehicle uploads an interaction result to the RSU after the V2V interaction. As shown in fig. 1, after the vehicles interact with V2V, the interaction results are transmitted to RSUs via V2I communication links, and a block link network is maintained between the RSUs, on which historical reputation values of the vehicles are recorded, and the vehicles on the road can request reputation values of opponent vehicles from the RSUs.
In this embodiment, when a vehicle receives a message broadcast by another vehicle, the credibility of the message needs to be determined according to the reputation value of the source vehicle. Considering that within a period, there may be vehicles that have first entered the VANET trust management system, no initial trust value is assigned to the vehicle that has just entered the vehicle trust management system. The improved three-value subjective logic algorithm is adopted to model the interaction result between vehicles, and the reputation value of one vehicle is evaluated by using historical interaction records. The reputation value is periodically updated and stored on the blockchain network built by the RSUs.
In the invention, considering that the VANET is larger and larger in scale, the centralized system can have the problems of single-point failure, network congestion and the like, so that a block chain network architecture is used for realizing the VANET trust management mechanism. And calculating the update of the reputation value of the vehicle by using an improved three-value-based subjective logic algorithm based on the interaction result between the vehicles. Considering that the VANET has extremely high requirement on time delay and a certain time is required for broadcasting information to the whole network by the blockchain network, the vehicle reputation value in the VANET is updated by a periodic updating method and then stored on the blockchain network maintained by the RSU. Considering that the vehicles request the trust relationship between themselves and other vehicles in two periods, in order to express the real trust relationship between the two vehicles more accurately, the reputation value of the vehicle at the end moment of the last period is combined with the interaction result of the vehicles in the current period, and the more accurate trust relationship between the two vehicles is finally obtained according to the multi-hop trust propagation rule.
Fig. 2 is a flowchart of a reputation updating method based on internet of vehicles in an embodiment of the present invention, and as shown in fig. 2, the method includes:
101. the road side unit receives the interactive information uploaded by different vehicles, verifies the interactive information and stores the vehicle information which is verified successfully;
after each V2V communication, the vehicle packages the communication resultAnd uploading the data packet with the fixed format to a nearby RSU as a basis for updating the reputation value in the vehicle in the period. The uploaded data packet comprises the identity information Cert of the opposite vehicleiTimestamp, and the interaction result. Expressed as:
wherein v isi→ RSU represents that vehicle i uploads the interaction result to nearby road side unit RSU, ωijRepresenting the trust opinion of the i car to the j car; alpha is alphaij,βij,γijThe evidences of i car to j car respectively represent the number of trusting, distrust and neutral evidences; a isijIndicating the inherent trust of the user i car to j car, e.g. if the opposing car is likely to be a police or ambulance, then the proportion of inherent trust for messages sent out by these cars is greater than for normal cars.
The RSU firstly receives the identity certificate Cert of the vehicle after receiving the information uploaded by the vehicleiAnd verifying the timestamp of the vehicle, and if the identity information of the vehicle is valid, storing the information. Otherwise, the identity of the vehicle is traced.
102. Classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle which enters the vehicle trust management system for the first time is included; acquiring all interactive information of a certain vehicle on a road side unit, taking the vehicle corresponding to the interactive information as a first classification set of the certain vehicle, judging whether the vehicle in the first classification set enters a vehicle trust management system for the first time, and taking the vehicle entering the vehicle trust management system for the first time as a second classification set;
and classifying the collected data. When the VANET trust management system updates the reputation value of a certain vehicle, the vehicle may have interacted with a plurality of vehicles in the current period, the RSU has the evaluation of the vehicles by the plurality of vehicles, and the set of vehicle interaction is recorded as a first classification set N. The vehicles which enter the VANET trust management system for the first time may be contained in the vehicles, and the system does not assign any initial reputation value to the vehicles. After the vehicles are classified, the set entering the vehicle reputation management system for the first time is recorded as a second classification set P.
103. And respectively calculating the reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle.
And calculating the reputation value of the vehicle by utilizing a three-value subjective logic algorithm and considering the reputation value of a period on the vehicle of the evaluator and the interaction frequency of the period between the vehicle and the target vehicle.
Wherein,representing the reputation value of x vehicles in the t-th period, N is the set of vehicles which have direct interaction with x vehicles in the t-th period, i.e. the current period, E (omega)ix) Is the expectation of i car to x car trust opinion during the t-th cycle,is the number of i car to x car interactions in the t-th cycle,indicates the reputation value, gamma, of the i car at the end of the t-1 th cycle1And gamma2Respectively, the reputation value of the last period and the weight factor occupied by the interaction frequency. Equation (2) shows that the interaction frequency and the last period reputation value of the evaluation vehicle are normalized to be considered as influencing factors. If the vehicle is evaluated as first entering the reputation management system, the system does not assign any voicesThe reputation value, if the set P is not empty, is calculated according to equation (3). The reputation value for x cars between the beginning of the t-th cycle and the end of the t-th cycle may eventually be derived.
The trust expectation between two users can be determined by using the trust opinion, which can be converted into the expression of formula (4), and the expectation is shown in formula (5).
Wherein, in the formula (5), b isij、dij、nij、eijRespectively formed by alphaij,βij,γijCalculated, so here ωijCan also be expressed as ωij={[bij,dij,nij,eij],aij},ωijRepresenting the trust opinion of the i car to the j car; bij、dij、nij、eijRespectively representing the credibility probability, the incredibility probability, the posterior uncertainty probability and the prior uncertainty probability of the i car to the j car, alphaij,βij,γijThe evidences of i car to j car respectively represent the number of trusting, distrust and neutral evidences; wherein the a priori uncertainty is due to a lack of evidence, in which case the default positive, negative, and neutral evidence amounts are each 1; a isijRepresenting the inherent trust of the user i car to j car, E (ω)ij) Representing a trust expectation between i and j cars.
In some embodiments, fig. 3 shows a flowchart of a reputation updating algorithm in a preferred embodiment of the present invention, and as shown in fig. 3, the reputation updating mainly includes:
collecting all interaction records of the vehicle i and other vehicles in the current period;
classifying the interactive vehicles of the vehicle i;
dividing the interactive vehicles of the vehicle i into vehicles containing the VANET participating in the first time and vehicles not containing the VANET participating in the first time;
updating the reputation value of the vehicle which initially participates in the VANET in the current period by using a formula (3);
the reputation value of the vehicle not containing the first participation in VANET during the current period is updated using equation (2).
In some preferred embodiments, at the end of a period, the reputation value in the period is already calculated in step 103, but the time of the period is short enough to reflect the true reputation value of the vehicle, On the other hand, some malicious attackers may use an On-off attack to perform a good increase of their reputation value for a certain period of time, then perform a malicious attack, and start performing a good again when the reputation value is reduced to a certain extent, thus generating a larger malicious influence. In this case, considering only the interactive feedback information in the current period cannot suppress such a behavior. In the invention, the influence of historical interactive information on the reputation value of the vehicle is considered, and the dynamic attenuation factor lambda is introduced to adjust the weight of the historical information, so that the principle that the reputation value is difficult to obtain and is volatile is realized.
In the formula (6), alpha, beta and delta are regulating factors, alpha represents a first regulating factor, beta represents a second regulating factor, and delta represents a third regulating factor; alpha determines the value range of the attenuation factor, and beta determines the attenuation factor according to the value rangeThe rate of change of delta determines the minimum value of the attenuation factor.
In some embodiments, α -0.4, β -10, and δ -0.1 are selected as adjustment factors according to the "rarely volatile" principleAnd therefore, the first and second electrodes are,when in useIn the process, the reputation generated by the interaction in the current period is higher than the historical value, and λ is increased but not more than 0.5, so that the interaction in the current period does not account for a high proportion in the final reputation value calculation, and the vehicle reputation value with good performance only slowly rises. On the contrary, the present invention is not limited to the above-described embodiments,then, the reputation value generated by the current performance is lower than the historical value, the lambda becomes smaller, and the final reputation is calculatedMay be weighted higher, quickly lowering the vehicle reputation value for poor behavior. The final reputation value for vehicle x is obtained by performing a calculation using equation (7).
Considering the situation that a vehicle requests a trust relationship with another vehicle between two periods, a search algorithm for searching a trust path between the two vehicles in the current period is designed, the trust relationship between the two vehicles in the current period is calculated by using the searched trust path, and the real trust relationship between the two vehicles can be accurately obtained by combining the reputation value of the vehicle in the previous period recorded on the block chain.
Fig. 4 is a flowchart of a method for calculating a trust level based on a vehicle networking in an embodiment of the present invention, as shown in the figure, the method includes:
201. the road side unit receives the interactive information uploaded by different vehicles, verifies the interactive information and stores the vehicle information which is verified successfully;
202. classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle which enters the vehicle trust management system for the first time is included; acquiring all interactive information of a certain vehicle on a road side unit, taking the vehicle corresponding to the interactive information as a first classification set of the certain vehicle, judging whether the vehicle in the first classification set enters a vehicle trust management system for the first time, and taking the vehicle entering the vehicle trust management system for the first time as a second classification set; 203. respectively calculating reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle;
204. and calculating a trust path between the vehicle and the target vehicle by utilizing a trust path search algorithm based on the reputation value of each vehicle.
Suppose that when the vehicle i receives a message from the opponent vehicle j at a certain time, the vehicle i needs to judge the credibility of the message according to the reputation value of the vehicle j. The vehicle i inquires the RSU about the reputation value of the current vehicle j at the end of the last period, but since the vehicle j has a certain amount of behaviors from the end of the last period to the current time and j transmits information to i in a short time, the distance between i and j can be inferred not to be very far, so that the reputation value of the j vehicle at the end of the last period is considered, and the interaction relation between the j vehicle and the i vehicle from the end of the last period to the current time is jointly considered to be used for calculating the trust relation between the i vehicle and the j vehicle. Therefore, the invention designs a trust path searching algorithm to inquire the trust path between the vehicle and the target vehicle in the current period, and considers the six-degree space separation theory to enable the searched trust path to more accurately express the trust relationship between the two vehicles.
The algorithm flow chart is shown in fig. 5. In the implementation process of the embodiment, an algorithm idea based on depth-first search is used for searching the trust path between two vehicles.
Calculating a trust relationship between the vehicle and the target vehicle based on the reputation value of the vehicle at the end of the previous period and the interaction relationship between the vehicle and the target vehicle from the end of the previous period to the current time, and forming a trust relationship matrix; searching a trust path from a source vehicle to a target vehicle from the trust relationship matrix; judging whether the reputation value is smaller than a threshold value, if so, removing the node, and updating the trust relationship matrix; if the trust relationship length is smaller than the maximum trust path length, continuously judging whether the trust relationship length is smaller than the maximum trust path length, if the trust relationship length is equal to or larger than the maximum trust path length, searching the trust path from the source vehicle to the target vehicle again, otherwise judging whether the target vehicle is found, and if the target vehicle is not found, continuously searching the trust path from the source vehicle to the target vehicle again; if the target vehicle is found, the trust path is increased by 1.
After the trust path between the source vehicle and the target vehicle is calculated, a graph matrix M is used to represent the trust path between the source vehicle and the target vehicle, and assuming that the trust path between the source vehicle i and the target vehicle j involves at most n other vehicles, the graph matrix M is represented as:
wherein, ω isijRepresents the trust opinion of i car to j car, omegaij={[αij,βij,γij],aij},αij,βij,γijThe evidences of i car to j car respectively represent the number of trusting, distrust and neutral evidences; a isijIndicating the inherent trust of the user i car to j car.
And calculating the trust relationship between the two vehicles from the end time of the last period to the current time. For the user i vehicle, the trust opinion of the i vehicle on all other vehicles in the k-times traversal process is expressed as:
in the formula,representing a trust relationship matrix of the i car at the k-th traversal, wherein the trust relationship matrix comprises trust opinions of the i car to other n users; k represents the number of traversals through the trust opinion matrix,representing the opinion vector for i car to j car after the k-th traversal. When k is a number of 1, the number of the transition metal,indicating a direct opinion. The opinion vector for user vehicle i may be iteratively updated using equation (10):
suppose that the opinion vector of i car to j car is updated from (k-1) round to k round toAn example, <' > an operator indicatesΔ, Θ are the decay and fusion operations of trust opinions, respectively.
If there is a serial trust relationship between the two (e.g., if i trusts k, k trusts j, then the trust sentiment from i to j will decay), the rule for decaying transitive trust is as follows:
ωij=Δ(ωik,ωkj)={[αij,βij,γij],aij} (11)
if the two trust opinions are in a parallel topological relation (if i has two trust opinions to j, the two trust opinions need to be fused in the final calculation), the rule for fusing the trust opinions is as follows:
assume that the maximum trust path length between i car and j car is set to 6 hops, so k is taken to be 6. Calculated by equation (8)Thus, the trust relationship between i and j is obtained
A final trust relationship between the two vehicles is calculated. And (4) calculating expectation of the obtained trust opinions between the two vehicles, and then combining the reputation value of the opposite vehicle j at the ending moment of the last period to obtain the trust relationship between the source vehicle i and the target vehicle j. From formulae (15) and (16):
E(ωij) Is the trust value between i car and j car; e (omega)ij)(t-1)Representing the trust value between the i car and the j car in the t period;representing the reputation value of the j car in the t-1 th cycle. Vehicle i according to E (ω)ij) To determine whether to accept the message from vehicle j. The specific judgment threshold value can be determined according to historical information of the Internet of vehicles, so that the method has better adaptability.
In the description of the present invention, it is to be understood that the terms "coaxial", "bottom", "one end", "top", "middle", "other end", "upper", "one side", "top", "inner", "outer", "front", "center", "both ends", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "disposed," "connected," "fixed," "rotated," and the like are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; the terms may be directly connected or indirectly connected through an intermediate, and may be communication between two elements or interaction relationship between two elements, unless otherwise specifically limited, and the specific meaning of the terms in the present invention will be understood by those skilled in the art according to specific situations.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A reputation updating method based on Internet of vehicles is characterized by comprising the following steps:
the road side unit receives the interactive information uploaded by different vehicles, verifies the interactive information and stores the vehicle information which is verified successfully;
classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle which enters the vehicle trust management system for the first time is included; acquiring all interactive information of a certain vehicle on a road side unit, taking the vehicle corresponding to the interactive information as a first classification set of the certain vehicle, judging whether the vehicle in the first classification set enters a vehicle trust management system for the first time, and taking the vehicle entering the vehicle trust management system for the first time as a second classification set;
and respectively calculating the reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle.
2. The reputation updating method based on the internet of vehicles as claimed in claim 1, wherein the mutual information uploaded by the vehicles comprises that after each V2V communication between vehicles, the communication result is packaged into a data packet of fixed format and uploaded to a nearby road side unit by using V2I communication as a basis for the reputation value updating of the vehicle in the period; the data packet uploaded by the vehicle comprises the identity information Cert of the vehicle interacted with by the vehicleiTimestamp, and the interaction result.
3. The reputation updating method based on internet of vehicles according to claim 1, wherein all interaction expectation values obtained by the vehicles after each period of interaction comprise the reputation value of the vehicle in the last period and the interaction frequency between the vehicle and other vehicles in the present period, and the reputation value of the vehicle in the first classification set or/and the second classification set is obtained in combination with the trust expectation between the vehicle and other vehicles.
4. The reputation updating method based on Internet of vehicles according to claim 3,
the vehicle reputation values in the first classification set are calculated in the following manner:
the vehicle reputation values in the second classification set are calculated in the following manner:
wherein,the reputation value of x vehicles in the t period is represented, and N represents a first classification set; p represents a second set of classifications; gamma ray1Is a weight factor, gamma, occupied by the reputation value of the previous period2Respectively is the weight factor occupied by the interactive frequency in the previous period;is the number of i car and x car interaction in the t cycle;the reputation value of the i car at the end of the t-1 th period is shown; e (omega)ix) Representing a trust expectation between i car and x car.
5. The reputation updating method based on internet of vehicles as claimed in claim 3, wherein the calculation mode of trust expectation between the vehicle and other vehicles is expressed asWherein, E (ω)ij) Representing a trust expectation between i cars to j cars; bijRepresenting the credibility probability of the i car to the j car; a isijRepresenting the inherent trust of i car to j car; n isijRepresenting posterior uncertainty probability of the vehicle i to the vehicle j; e.g. of the typeijRepresenting the a priori uncertainty probability of i car to j car.
6. The reputation updating method based on Internet of vehicles as claimed in claim 3, further comprising weighting and summing the calculated reputation value of the vehicle in the current period and the reputation value of the vehicle in the previous period by using a dynamic attenuation factor, and outputting the weighted and summed reputation value as the reputation value of the vehicle in the new current period, wherein the calculation formula of the dynamic attenuation factor λ is expressed asα represents a first adjustment factor, β represents a second adjustment factor, and δ represents a third adjustment factor;representing the reputation value of x cars in the t-th period;indicating the reputation value of x cars in the t-1 th cycle.
7. A trust calculation method based on Internet of vehicles is characterized by comprising the following steps:
the road side unit receives the interactive information uploaded by different vehicles, verifies the interactive information and stores the vehicle information which is verified successfully;
classifying all interactive vehicles corresponding to the current vehicle according to whether the vehicle entering the vehicle trust management system for the first time is included, namely acquiring all interactive information of a certain vehicle on a road side unit, taking the vehicle corresponding to the interactive information as a first classification set of the certain vehicle, judging whether the vehicle in the first classification set enters the vehicle trust management system for the first time or not, and taking the vehicle entering the vehicle trust management system for the first time as a second classification set;
respectively calculating reputation values of the vehicles in the first classification set and the vehicles in the second classification set by using a three-value subjective logic algorithm to obtain all interaction opinion expected values obtained after the vehicles interact in each period, and updating the reputation value of each vehicle;
and calculating a trust path between the vehicle and the target vehicle by utilizing a trust path search algorithm based on the reputation value of each vehicle.
8. The vehicle networking based trust calculation method of claim 7, wherein the calculating the trust path between the vehicle and the target vehicle by using the trust path search algorithm further comprises the road side unit selecting a block updater by using a consensus algorithm to pack transactions in the resource pool and form a new block, and the mineworker node broadcasts information of the block and forms distributed storage of the reputation database in a block chain for inquiring the reputation value information of each vehicle at the end of the previous period.
9. The internet-of-vehicles-based trust calculation method according to claim 7, wherein the calculating the trust path between the vehicle and the target vehicle by using the trust path search algorithm comprises updating the trust path between the vehicle and the target vehicle by using a trust decay rule when the trust paths are connected in series; and when the trust paths are connected in parallel, updating the trust paths between the vehicles and the target vehicle by adopting a trust fusion rule.
10. The internet-of-vehicles-based trust calculation method according to claim 7, wherein the calculating of the trust path between the vehicle and the target vehicle by using the trust path search algorithm further comprises calculating the trust relationship between the vehicle and the target vehicle based on the reputation value of the vehicle at the end of the previous period and the interaction relationship between the vehicle and the target vehicle from the end time of the previous period to the current time, and forming a trust relationship matrix; searching a trust path from a source vehicle to a target vehicle from the trust relationship matrix; judging whether the reputation value is smaller than a threshold value, if so, removing the node, and updating the trust relationship matrix; if the trust relationship length is smaller than the maximum trust path length, continuously judging whether the trust relationship length is smaller than the maximum trust path length, if the trust relationship length is equal to or larger than the maximum trust path length, searching the trust path from the source vehicle to the target vehicle again, otherwise judging whether the target vehicle is found, and if the target vehicle is not found, continuously searching the trust path from the source vehicle to the target vehicle again; if the target vehicle is found, the trust path is increased by 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110582032.7A CN113380024B (en) | 2021-05-27 | 2021-05-27 | Reputation updating method and trust calculation method based on Internet of vehicles |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110582032.7A CN113380024B (en) | 2021-05-27 | 2021-05-27 | Reputation updating method and trust calculation method based on Internet of vehicles |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113380024A true CN113380024A (en) | 2021-09-10 |
CN113380024B CN113380024B (en) | 2022-09-02 |
Family
ID=77572099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110582032.7A Active CN113380024B (en) | 2021-05-27 | 2021-05-27 | Reputation updating method and trust calculation method based on Internet of vehicles |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113380024B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114945022A (en) * | 2022-05-20 | 2022-08-26 | 重庆邮电大学 | Internet of vehicles edge calculation sharing method based on block chain |
CN115694930A (en) * | 2022-10-18 | 2023-02-03 | 重庆邮电大学 | Internet of vehicles malicious vehicle node behavior detection method based on credibility management |
Citations (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103561047A (en) * | 2013-07-31 | 2014-02-05 | 南京理工大学 | P2P network trust cloud model calculating method based on interest groups |
CN104363626A (en) * | 2014-11-07 | 2015-02-18 | 中国人民武装警察部队工程大学 | Bayesian theory based credible routing method for VANET (vehicular ad-hoc network) |
CN104486741A (en) * | 2014-12-13 | 2015-04-01 | 重庆邮电大学 | Trust state perceiving mixed service discovery method |
CN106161440A (en) * | 2016-07-04 | 2016-11-23 | 中国人民武装警察部队工程大学 | Based on D S evidence and the multi-area optical network trust model of theory of games |
CN107396293A (en) * | 2017-08-03 | 2017-11-24 | 重庆邮电大学 | V2X resource allocation methods and system based on D2D communications |
CN107509228A (en) * | 2017-07-24 | 2017-12-22 | 长安大学 | A kind of data trusted transmission method under car networking |
CN107665405A (en) * | 2017-09-26 | 2018-02-06 | 北京邮电大学 | A kind of vehicle credit management method and device |
CN107750053A (en) * | 2017-05-25 | 2018-03-02 | 天津大学 | Based on multifactor wireless sensor network dynamic trust evaluation system and method |
WO2018063268A1 (en) * | 2016-09-30 | 2018-04-05 | Nokia Technologies Oy | Updating security key |
CN108632784A (en) * | 2018-04-17 | 2018-10-09 | 上海电机学院 | A kind of vehicle-mounted credible route computing method of net of sub-clustering |
CN108882273A (en) * | 2018-10-10 | 2018-11-23 | 南京工业大学 | Coexistence mechanism of weak credible nodes under wireless Mesh network opportunistic routing |
CN109327911A (en) * | 2018-11-30 | 2019-02-12 | 重庆邮电大学 | Recognize the frequency spectrum switching method based on credit system in heterogeneous wireless network |
CN109347852A (en) * | 2018-11-07 | 2019-02-15 | 暨南大学 | A kind of car networking method for evaluating trust of lightweight |
CN109862114A (en) * | 2019-03-12 | 2019-06-07 | 南京邮电大学 | A kind of safety vehicle intelligent perception method calculated based on mist |
CN110198288A (en) * | 2018-02-27 | 2019-09-03 | 中兴通讯股份有限公司 | A kind of processing method and equipment of abnormal nodes |
CN110324362A (en) * | 2019-06-12 | 2019-10-11 | 南京优慧信安科技有限公司 | A kind of block chain User reliability evaluation method based on interbehavior |
CN110445788A (en) * | 2019-08-09 | 2019-11-12 | 西安电子科技大学 | The trust evaluation system and method for content oriented under a kind of vehicular ad hoc network environment |
EP3614713A1 (en) * | 2017-04-21 | 2020-02-26 | LG Electronics Inc. -1- | V2x communication device and data communication method thereof |
AU2018308958A1 (en) * | 2018-10-12 | 2020-04-30 | Jinan University | An aggregated trust evaluation method for message reliability in vanets |
CN111093189A (en) * | 2019-12-06 | 2020-05-01 | 暨南大学 | Emergency message dissemination method and system based on trust cascade in Internet of vehicles |
CN111263331A (en) * | 2020-01-16 | 2020-06-09 | 长安大学 | Internet of vehicles node reputation evaluation method based on crowd sensing |
CN111447177A (en) * | 2020-03-02 | 2020-07-24 | 西北工业大学 | Vehicle networking trust management method based on block chain |
CN111885539A (en) * | 2020-07-23 | 2020-11-03 | 杭州师范大学 | Internet of vehicles credit updating method based on dynamic adjustment of updating interval |
WO2020258060A2 (en) * | 2019-06-25 | 2020-12-30 | 南京邮电大学 | Blockchain-based privacy protection trust model for internet of vehicles |
CN112188467A (en) * | 2020-09-29 | 2021-01-05 | 重庆邮电大学 | Terminal discovery method based on user attributes |
CN112489458A (en) * | 2020-11-05 | 2021-03-12 | 暨南大学 | Credible privacy protection intelligent traffic light method and system based on V2X technology |
-
2021
- 2021-05-27 CN CN202110582032.7A patent/CN113380024B/en active Active
Patent Citations (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103561047A (en) * | 2013-07-31 | 2014-02-05 | 南京理工大学 | P2P network trust cloud model calculating method based on interest groups |
CN104363626A (en) * | 2014-11-07 | 2015-02-18 | 中国人民武装警察部队工程大学 | Bayesian theory based credible routing method for VANET (vehicular ad-hoc network) |
CN104486741A (en) * | 2014-12-13 | 2015-04-01 | 重庆邮电大学 | Trust state perceiving mixed service discovery method |
CN106161440A (en) * | 2016-07-04 | 2016-11-23 | 中国人民武装警察部队工程大学 | Based on D S evidence and the multi-area optical network trust model of theory of games |
WO2018063268A1 (en) * | 2016-09-30 | 2018-04-05 | Nokia Technologies Oy | Updating security key |
EP3614713A1 (en) * | 2017-04-21 | 2020-02-26 | LG Electronics Inc. -1- | V2x communication device and data communication method thereof |
CN107750053A (en) * | 2017-05-25 | 2018-03-02 | 天津大学 | Based on multifactor wireless sensor network dynamic trust evaluation system and method |
CN107509228A (en) * | 2017-07-24 | 2017-12-22 | 长安大学 | A kind of data trusted transmission method under car networking |
CN107396293A (en) * | 2017-08-03 | 2017-11-24 | 重庆邮电大学 | V2X resource allocation methods and system based on D2D communications |
CN107665405A (en) * | 2017-09-26 | 2018-02-06 | 北京邮电大学 | A kind of vehicle credit management method and device |
CN110198288A (en) * | 2018-02-27 | 2019-09-03 | 中兴通讯股份有限公司 | A kind of processing method and equipment of abnormal nodes |
CN108632784A (en) * | 2018-04-17 | 2018-10-09 | 上海电机学院 | A kind of vehicle-mounted credible route computing method of net of sub-clustering |
CN108882273A (en) * | 2018-10-10 | 2018-11-23 | 南京工业大学 | Coexistence mechanism of weak credible nodes under wireless Mesh network opportunistic routing |
AU2018308958A1 (en) * | 2018-10-12 | 2020-04-30 | Jinan University | An aggregated trust evaluation method for message reliability in vanets |
CN109347852A (en) * | 2018-11-07 | 2019-02-15 | 暨南大学 | A kind of car networking method for evaluating trust of lightweight |
CN109327911A (en) * | 2018-11-30 | 2019-02-12 | 重庆邮电大学 | Recognize the frequency spectrum switching method based on credit system in heterogeneous wireless network |
CN109862114A (en) * | 2019-03-12 | 2019-06-07 | 南京邮电大学 | A kind of safety vehicle intelligent perception method calculated based on mist |
CN110324362A (en) * | 2019-06-12 | 2019-10-11 | 南京优慧信安科技有限公司 | A kind of block chain User reliability evaluation method based on interbehavior |
WO2020258060A2 (en) * | 2019-06-25 | 2020-12-30 | 南京邮电大学 | Blockchain-based privacy protection trust model for internet of vehicles |
CN110445788A (en) * | 2019-08-09 | 2019-11-12 | 西安电子科技大学 | The trust evaluation system and method for content oriented under a kind of vehicular ad hoc network environment |
CN111093189A (en) * | 2019-12-06 | 2020-05-01 | 暨南大学 | Emergency message dissemination method and system based on trust cascade in Internet of vehicles |
CN111263331A (en) * | 2020-01-16 | 2020-06-09 | 长安大学 | Internet of vehicles node reputation evaluation method based on crowd sensing |
CN111447177A (en) * | 2020-03-02 | 2020-07-24 | 西北工业大学 | Vehicle networking trust management method based on block chain |
CN111885539A (en) * | 2020-07-23 | 2020-11-03 | 杭州师范大学 | Internet of vehicles credit updating method based on dynamic adjustment of updating interval |
CN112188467A (en) * | 2020-09-29 | 2021-01-05 | 重庆邮电大学 | Terminal discovery method based on user attributes |
CN112489458A (en) * | 2020-11-05 | 2021-03-12 | 暨南大学 | Credible privacy protection intelligent traffic light method and system based on V2X technology |
Non-Patent Citations (10)
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114945022A (en) * | 2022-05-20 | 2022-08-26 | 重庆邮电大学 | Internet of vehicles edge calculation sharing method based on block chain |
CN114945022B (en) * | 2022-05-20 | 2023-05-23 | 重庆邮电大学 | Block chain-based Internet of vehicles edge computing sharing method |
CN115694930A (en) * | 2022-10-18 | 2023-02-03 | 重庆邮电大学 | Internet of vehicles malicious vehicle node behavior detection method based on credibility management |
CN115694930B (en) * | 2022-10-18 | 2024-03-26 | 重庆邮电大学 | Internet of vehicles malicious vehicle node behavior detection method based on credibility management |
Also Published As
Publication number | Publication date |
---|---|
CN113380024B (en) | 2022-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhao et al. | A fuzzy logic-based intelligent multiattribute routing scheme for two-layered SDVNs | |
Xia et al. | An attack-resistant trust inference model for securing routing in vehicular ad hoc networks | |
Chen et al. | Delay-aware grid-based geographic routing in urban VANETs: A backbone approach | |
Movahedi et al. | Trust-distortion resistant trust management frameworks on mobile ad hoc networks: A survey | |
Zhang et al. | AATMS: An anti-attack trust management scheme in VANET | |
Saad et al. | Hedonic coalition formation for distributed task allocation among wireless agents | |
Wang et al. | A novel reputation-aware client selection scheme for federated learning within mobile environments | |
Asheralieva et al. | Reputation-based coalition formation for secure self-organized and scalable sharding in IoT blockchains with mobile-edge computing | |
CN113380024B (en) | Reputation updating method and trust calculation method based on Internet of vehicles | |
Xia et al. | Towards a novel trust‐based multicast routing for VANETs | |
Hossain et al. | Multi-objective Harris hawks optimization algorithm based 2-Hop routing algorithm for CR-VANET | |
Machado et al. | Blockchain incentivized data forwarding in MANETs: Strategies and challenges | |
Rawat et al. | Joint beacon frequency and beacon transmission power adaptation for internet of vehicles | |
Al-Hamid et al. | Vehicular intelligence: Towards vehicular network digital-twin | |
CN109982327A (en) | A kind of ad hoc network communication method, device, equipment and readable storage medium storing program for executing | |
Yang et al. | Navigation route based stable clustering for vehicular ad hoc networks | |
Jiao et al. | Proactive content delivery for vehicles over cellular networks: The fundamental benefits of computing and caching | |
Kait et al. | Fuzzy logic‐based trusted routing protocol using vehicular cloud networks for smart cities | |
Manzo et al. | Deepndn: Opportunistic data replication and caching in support of vehicular named data | |
CN115022883A (en) | Block chain-based Internet of vehicles trust management method for resisting collusion attack | |
HaghighiFard et al. | Hierarchical federated learning in multi-hop cluster-based vanets | |
Lamaazi et al. | Trust-3dm: trustworthiness-based data-driven decision-making framework using smart edge computing for continuous sensing | |
Xiao | [Retracted] Load Balancing Selection Method and Simulation in Network Communication Based on AHP‐DS Heterogeneous Network Selection Algorithm | |
Sarangi | Malicious Attacks Detection Using Trust Node Centric Weight Management Algorithm in Vehicular Platoon | |
Mirzaee et al. | CHFL: A collaborative hierarchical federated intrusion detection system for vehicular networks |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |