Visible to the public Learning-Based Rogue Edge Detection in VANETs with Ambient Radio Signals

TitleLearning-Based Rogue Edge Detection in VANETs with Ambient Radio Signals
Publication TypeConference Paper
Year of Publication2018
AuthorsLu, X., Wan, X., Xiao, L., Tang, Y., Zhuang, W.
Conference Name2018 IEEE International Conference on Communications (ICC)
Keywordsaccess protocols, ambient radio signals, authentication, composability, detection error rate reduction, detection scheme, dynamic VANET, edge computing, edge detection, Image edge detection, indoor radio, indoor wireless networks, large-scale network infrastructure, learning (artificial intelligence), learning-based rogue edge detection, MAC address, man-in-the-middle attacks, Metrics, mobile device, Mobile handsets, OBUs, onboard units, optimal detection policy, PHY-layer rogue edge detection scheme, physical-layer rogue edge detection, pubcrawl, Q-learning based detection scheme, received ambient signal properties, Received signal strength indicator, reinforcement learning technique, resilience, Resiliency, roadside units, rogue edge attacks, rogue edge node, RSSI, RSUs, Scalability, security, serving edge, shared ambient radio, signal detection, source media access control address, spoofing detection, telecommunication computing, telecommunication security, test threshold, VANET model, vehicular ad hoc networks, wireless networks
AbstractEdge computing for mobile devices in vehicular ad hoc networks (VANETs) has to address rogue edge attacks, in which a rogue edge node claims to be the serving edge in the vehicle to steal user secrets and help launch other attacks such as man-in-the-middle attacks. Rogue edge detection in VANETs is more challenging than the spoofing detection in indoor wireless networks due to the high mobility of onboard units (OBUs) and the large-scale network infrastructure with roadside units (RSUs). In this paper, we propose a physical (PHY)- layer rogue edge detection scheme for VANETs according to the shared ambient radio signals observed during the same moving trace of the mobile device and the serving edge in the same vehicle. In this scheme, the edge node under test has to send the physical properties of the ambient radio signals, including the received signal strength indicator (RSSI) of the ambient signals with the corresponding source media access control (MAC) address during a given time slot. The mobile device can choose to compare the received ambient signal properties and its own record or apply the RSSI of the received signals to detect rogue edge attacks, and determines test threshold in the detection. We adopt a reinforcement learning technique to enable the mobile device to achieve the optimal detection policy in the dynamic VANET without being aware of the VANET model and the attack model. Simulation results show that the Q-learning based detection scheme can significantly reduce the detection error rate and increase the utility compared with existing schemes.
Citation Keylu_learning-based_2018