Under the cellular vehicle-to-everything (C-V2X) communication technology framework,the accuracy of basic safety messages (BSM) is crucial for ensuring road traffic safety.However,BSM data is susceptible to non-malicious factors such as sensor faults or environmental disturbances,leading to data anomalies that may misguide driving decisions.In response to this issue,two-phase learning strategy for correcting anomalies in BSM was proposed.In the first phase,an unsupervised hybrid generative model was used to learn the behavior patterns and distribution characteristics of normal BSM data and a memory module was introduced to construct a fine-grained prototype repository in the feature space for enhancing the model’s understanding of the diversity of normal behavior patterns.In the second phase,based on the network parameters obtained in the first phase,a self-supervised learning strategy was employed for data correction.Results show that the proposed solution exhibits good correction capability and significantly reduces the error in BSM.
在生成器的编码网络中,当提供编码为的输入查询时,为从最后一个线性层输出的向量维度。如式(11)所示,存储网络获得输出向量,该输出向量代表着记忆单元si 的加权平均值。而这里的权重向量( p ∈RM )是通过计算查询和每个记忆单元之间的归一化相似度导出的,pi 代表 p 的第i个权重,如式(12)所示。
在本文的研究中,使用以下指标来评估提出的模型性能:召回率如式(15)所示,也称为真阳性率,它反映了模型准确识别阳性类样本的能力。F1分数如式(16)所示,用作精度和召回率的调和平均值,旨在不牺牲精度的情况下最大限度地提高召回率。此外,实验还通过受试者工作特征(receiver operating characteristic,ROC)曲线下的面积(area under curve,AUC)来评估ProtoNet模型区分阳性和阴性类别的能力。最后,使用平均误差距离来评估AnoRectify模型对异常BSM数据校正的能力,如式(17)所示。
HurD, LeeD, OhJ,et al.Survey on challenges and solutions of C-V2X:LTE-V2X communication technology[C]//2023 Fourteenth International Conference on Ubiquitous and Future Networks.Paris:IEEE,2023:639-641.
[2]
ChenS Z, HuJ L, ShiY,et al.A vision of C-V2X:technologies,field testing,and challenges with Chinese development[J].IEEE Internet of Things Journal,2020,7(5):3872-3881.
[3]
XuX L, LiH Y, XuW J,et al.Artificial intelligence for edge service optimization in internet of vehicles:a survey[J].Tsinghua Science and Technology,2022,27(2):270-287.
[4]
GhalebF A, ZainalA, RassamM.Data verification and misbehavior detection in vehicular ad-hoc networks[J].Journal technology,2015,73(2):37-44.
[5]
KerracheC A, LagraaN, HussainR,et al.TACASHI:trust-aware communication architecture for social Internet of vehicles[J].IEEE Internet of Things Journal,2019,6(4):5870-5877.
[6]
LuR X, ZhangL, NiJ B,et al.5G vehicle-to-everything services:gearing up for security and privacy[J].Proceedings of the IEEE,2020,108(2):373-389.
[7]
DibaeiM, ZhengX, XiaY H,et al.Investigating the prospect of leveraging blockchain and machine learning to secure vehicular networks:a survey[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(2):683-700.
[8]
BoualouacheA, EngelT.A survey on machine learning-based misbehavior detection systems for 5G and beyond vehicular networks[J].IEEE Communications Surveys & Tutorials,2023,25(2):1128-1172.
[9]
BoualouacheA, EngelT.Federated learning-based scheme for detecting passive mobile attackers in 5G vehicular edge computing[J].Annals of Telecommunications,2022,77(3):201-220.
[10]
KhandelwalS, ShreejithS.A lightweight multi-attack CAN intrusion detection system on hybrid FPGAs[C]//2022 32nd International Conference on Field-Programmable Logic and Applications.Belfast:IEEE,2022:425-429.
[11]
AcharyaA, OluochJ.A dual approach for preventing blackhole attacks in vehicular ad hoc networks using statistical techniques and supervised machine learning[C]//2021 IEEE International Conference on Electro Information Technology.Mt.Pleasant:IEEE,2021:230-235.
[12]
SharshembievK, YooS M, ElmahdiE.Protocol misbehavior detection framework using machine learning classification in vehicular Ad Hoc networks[J].Wireless Networks,2021,27(3):2103-2118.
YangY H, WeiL J, WuJ,et al.A blockchain-based multidomain authentication scheme for conditional privacy preserving in vehicular ad-hoc network[J].IEEE Internet of Things Journal,2022,9(11):8078-8090.
[15]
SharmaA B, GolubchikL, GovindanR.Sensor faults[J].ACM Transactions on Sensor Networks,2010,6(3):1-39.
[16]
RealpeM, VintimillaB, VlacicL.Sensor fault detection and diagnosis for autonomous vehicles[J].MATEC Web of Conferences,2015,30:04003.
[17]
FeiH, XiaoF, LiG H,et al.An anomaly detection method of wireless sensor network based on multi-modals data stream[J].Chinese Journal of Computer,2017,40(8): 1829-1842.
[18]
GoodfellowI, Pouget-AbadieJ, MirzaM,et al.Generative adversarial nets[J].Advances in Neural Information Processing Systems,2014,27:2672-2680.
ZhangY X, WangJ D, ChenY Q,et al.Adaptive memory networks with self-supervised learning for unsupervised anomaly detection[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(12):12068-12080.