International Journal of Network Security & Its Applications (IJNSA)
ISSN: 0974 - 9330 (Online); 0975 - 2307 (Print)
Webpage URL: https://airccse.org/journal/ijnsa.html
A Risk-Aware Deep Reinforcement Learning Framework for AI-Driven Intrusion Detection and Adaptive Response in Autonomous Vehicles
Muhammad Faisal Shafiq1, Muhammad Irshad2 and Muhammad Naveed Sajjad3, 1Lucid Motors, Saudi Arabia 2RMG Company, Saudi Arabia, 3Yanal Finance Company, Saudi Arabia
Abstract
Autonomous vehicles expose in-vehicle networks to sophisticated intrusion threats. Although deep learning-based intrusion detection systems achieve high accuracy, most approaches remain detection centric and do not address adaptive mitigation under real-time constraints. This paper proposes a multilayer AI-driven framework integrating temporal deep learning, contextual risk modeling, and deep reinforcement learning-based mitigation. A hybrid CNN–BiLSTM model captures spatial payload characteristics and bidirectional temporal dependencies in CAN sequences. Detection output feeds a risk aware formulation fusing attack probability with ECU criticality, vehicle speed, and safety indicators. A Deep Q-Network learns mitigation policies minimizing residual system damages. Evaluation on the HCRL car-hacking dataset demonstrates strong detection performance. The adaptive policy reduces average system damage cost by 54.63% compared to static monitoring. End-to-end latency of 0.0205 ms per sample satisfies real-time constraints. By integrating detection, severity modeling, and adaptive response, the proposed architecture advances intrusion detection toward intelligent cyber-physical mitigation for resilient autonomous vehicles.
Keywords
Autonomous vehicles, Controller Area Network (CAN), Intrusion Detection System (IDS), Deep Learning, CNN–BiLSTM, Risk-Aware Modeling, Deep Reinforcement Learning, Adaptive Mitigation, Cyber-Physical Security, Real-Time Systems
Original Source URL: https://aircconline.com/ijnsa/V18N2/18226ijnsa07.pdf
Volume URL: https://airccse.org/journal/jnsa26_current.html
No comments:
Post a Comment