Federated learning-based scheme for detecting passive mobile attackers in 5G vehicular edge computing

Abstract

Detecting passive attacks is always considered difficult in vehicular networks. Passive attackers can eavesdrop on the wireless medium to collect beacons. These beacons can be exploited to track the positions of vehicles not only to violate their location privacy but also for criminal purposes. In this paper, we propose a novel federated learning-based scheme for detecting passive mobile attackers in 5G Vehicular Edge Computing. We first identify a set of strategies that can be used by attackers to efficiently track vehicles without being visually detected. We then build an efficient Machine Learning (ML) model to detect tracking attacks based only on the receiving beacons. Our scheme enables Federated Learning (FL) at the edge to ensure collaborative learning while preserving the privacy of vehicles. Moreover, FL clients use a semi-supervised learning approach to ensure accurate self-labeling. Our experiments demonstrate the effectiveness of our proposed scheme to detect passive mobile attackers quickly and with high accuracy. Indeed, only 20 received beacons are required to achieve 95% accuracy. This accuracy can be achieved within 60 FL rounds using 5 FL clients in each FL round. The obtained results are also validated through simulations.

Federated Learning-Based Detection and Control Mechanism of In-Car Navigation Safety System

“…The training process occurs on the individual vehicles, ensuring that sensitive information remains on the device and is not exposed to external parties. This decentralized approach enhances data privacy and addresses concerns about sharing personal driving data [21][22]. Once the local training is complete, the updated model parameters are securely aggregated without revealing the specific data from each vehicle.…”

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

“…3) Detection Mechanism: In addition to using encryption algorithms, privacy is also protected by designing defense mechanisms including attack detection and data leakage detection. In [189], a FL-based architecture for detecting passive attackers who eavesdrop on vehicles' information is proposed. Besides, the author first simulates passive attackers through synthetic data and position-feature extraction method, and consequently uses a semi-supervised method to self-label data in FL vehicles to obtain precise detection results in a short amount of time.…”

Federated learning-based detection and control mechanism of in-car navigation safety system

“…The training process occurs on the individual vehicles, ensuring that sensitive information remains on the device and is not exposed to external parties. This decentralized approach enhances data privacy and addresses concerns about sharing personal driving data [21,22]. Once the local training is complete, the updated model parameters are securely aggregated without revealing the speci c data from each vehicle.…”