Academic Journal of Computing & Information Science, 2023, 6(11); doi: 10.25236/AJCIS.2023.061110.
Xiaotong Zhou
School of Management and Engineering, Capital University of Economics and Business, Beijing, China
Based on the threat to user privacy posed by intelligent vehicle networks, this paper proposes an intelligent vehicle wireless communication attack detection algorithm based on air interface traffic identification. The technique determines whether there is a threat to user privacy by monitoring the vehicle network communication signals, analyzing the signals and the type of business being carried, and combining the type of business with whether it has the attribute of steganography attack, which includes location tracking, wireless eavesdropping and video echo of eavesdropping. Using the software radio platform, the wireless air interface electrical signals are collected and transmitted to the signal analysis platform, and the neural network model based on the CNN model achieves the identification of the three types of traffic: audio, image and video, and the accuracy of the simulation experiment results is 90.34%.
Smart Vehicle Security Risk, Internet of Vehicles, Abnormal Traffic Identification, CNN Neural Network, Wireless Attack Detection
Xiaotong Zhou. An Algorithm for Detecting Wireless Communication Attacks on Intelligent Vehicles Based on Air Interface Identification. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 11: 72-82. https://doi.org/10.25236/AJCIS.2023.061110.
[1] Miller C, Valasek C. Remote exploitation of an unaltered passenger vehicle [J]. Black Hat USA, 2015.
[2] Woo S, Jo H J, Lee D H. A practical wireless attack on the connected car and security protocol for in-vehicle CAN [J]. Intelligent Transportation Systems, IEEE Transactions on, 2015, 16(2): 993-1006.
[3] Francillon A, Danev B, Capkun S. Relay Attacks on Passive Keyless Entry and Start Systems in Modern Cars[C]//NDSS. 2011.
[4] Hyun J, Li J, Im C T, et al. A VoLTE traffic classification method in LTE network[C]. The 16th Asia-Pacific Network Operations and Management Symposium. IEEE, 2014: 1-6.
[5] Wang Z. The applications of deep learning on traffic identification[J]. BlackHat USA, 2015, 24(11): 1-10.
[6] Qian B, Lu S. Detection of mobile network abnormality using deep learning models on massive network measurement data[J]. Computer Networks, 2021, 201: 108571.
[7] Sengupta S, Yadav V K, Saraf Y, et al. MoViDiff: Enabling service differentiation for mobile video apps[C]. 2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM). IEEE, 2017: 537-543.
[8] Dong C, Zhang C, Lu Z, et al. CETAnalytics: Comprehensive effective traffic information analytics for encrypted traffic classification[J]. Computer Networks, 2020, 176: 107258.
[9] Aceto G, Ciuonzo D, Montieri A, et al. Mobile encrypted traffic classification using deep learning[C]. 2018 Network traffic measurement and analysis conference (TMA). IEEE, 2018: 1-8.
[10] Z. Geng, H. Yan, J. Zhang and D. Zhu, "Deep-Learning for Radar: A Survey," in IEEE Access, vol. 9, pp. 141800-141818, 2021, doi: 10.1109/ACCESS.2021.3119561.
[11] Qin Jiawei, Zhang Hua, Yan Hanbing, He Nengqiang, Tu Tengfei. Context-aware Android application vulnerability detection research [J]. Journal of Communication, 2021, 42(11):13-27.