Critical safety functions in modern vehicles rely heavily on intra-vehicle networks (IVNs), primarily via the Controller Area Network (CAN) protocol. The inherent vulnerabilities of CAN require robust intrusion detection systems (IDS) to mitigate adversarial threats. However, state-of-the-art IDS, especially AI-based approaches, often lack a comprehensive, well-defined performance analysis method. This work proposes and evaluates a structured pipeline for in-vehicle IDS, analyzing an autoencoder semi-supervised IDS as a practical case study. The method is validated on publicly available datasets, covering multiple attack types, with additional analysis of generalization capabilities. Performance is rigorously assessed using precision, recall, F1-score, and the Matthews Correlation Coefficient (MCC), chosen for its robustness in imbalanced scenarios. Results demonstrated highly efficient identification of DoS attacks (MCC 1.00), though Fuzzy DoS detection showed lower performance (MCC 0.214 in CAN-MIRGU and 0.074 in CAN-MODES). These findings support the viability of the proposed pipeline for IDS analysis focusing on enhancing CAN network security, consistent with recent research trends.
Lucas Melo da Silva Alves, Alexandre dos Santos Roque, E. P. de Freitas· International Conference on...· 0 citations
Vehicular Ad-Hoc Networks (VANETs) enable realtime communication for safety-critical applications including collision avoidance and traffic control. Their decentralized, dynamic architecture, however, makes them vulnerable to multiple attack classes, including Sybil, spoofing, Denial-of-Service (DoS), and other cyber threats. Existing defenses typically address cyber and physical layers independently, limiting their ability to capture the interplay between mobility patterns and attack propagation. This paper presents a cyber-physical simulation framework integrating vehicular mobility with the CybORG environment for multi-class attack mitigation. A Road Side Unit (RSU) acts as the infrastructure-based defender, monitoring vehicle behavior, maintaining trust scores, and executing defense actions via a Dueling Double Deep Q-Network with Prioritized Experience Replay (D3QN-PER). The agent learns optimal policies through environment interaction rather than static labeled data. Evaluation against two unsupervised baselines, Exponentially Weighted Moving Average (EWMA) and Trust-Gated Isolation Forest, demonstrates perfect detection performance (Recall = 100%, $\mathbf{F} \mathbf{1} \boldsymbol{=} \mathbf{1. 0 0 0 0})$ with zero false positives and zero false negatives, compared to 95.12% recall (EWMA) and 84.95% recall (Isolation Forest). The framework handles up to six concurrent attackers within the RSU's 200 m range with sub-millisecond latency, establishing a foundation for intelligent, adaptive security in vehicular networks.
Fasna Nadeera Irumpidamkandiyil Pocker, Farsana Ansari, Alexandre dos Santos Roque et al.· International Conference on...· 0 citations