Communication-Aware Quantum-Inspired Reinforcement Learning for Cyber-Resilient V2X Intrusion Detection and Mitigation

Q: Which performance aspects does the framework aim to improve?

The framework targets detection accuracy while reducing end-to-end delay and channel congestion (CBR). It also uses a cost function that penalizes false negatives, false positives, delay, packet loss, and RSU overload to maintain practical deployment behavior on edge systems.

Jul 16, 2026

Upload by Patrick

Smart cities increasingly rely on dense edge, IoT, and vehicular networks to provide traffic control, connected mobility, infrastructure monitoring, and energy management through the Internet of Vehicles (IoV). This connectivity expands the attack surface and enables cyber threats that can undermine safety, privacy, integrity, and service continuity. Static defenses struggle to adapt to evolving, multi-stage intrusions. The paper introduces CA-QIRL, a communication-aware quantum-inspired reinforcement learning framework using a lightweight deep Q-network, formulated as a communication-aware MDP for autonomous V2X mitigation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

Introduction

Problem background and threat model

Motivation for adaptive, real-time edge defense

Related work and limitations

Communication-Aware Quantum-Inspired Reinforcement Learning for Cyber-Resilient V2X Intrusion Detection and Mitigation Sajid Anwera , Rohan Farooqb , Anwar Shahb,∗ and Tallha Akrama a Department of Software Engineering, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Saudi Arabia b Department of Computer Science, National University of Computer and Emerging Sciences, Pakistan ARTICLE INFO Keywords: Smart Cities Internet of Vehicles (IoV) Cyber Defense Reinforcement Learning Quantum Computing 11 Jul 2026 AB STRACT Smart cities increasingly depend on dense edge, IoT, and vehicular networks to deliver critical urban services, including traffic control, connected mobility, infrastructure monitoring, and energy management. In this ecosystem, the Internet of Vehicles (IoV) is central to intelligent transportation, enabling continuous communication among vehicles, roadside infrastructure, and cloud-edge platforms. This connectivity, however, also enlarges the attack surface and exposes smart city and vehicular systems to evolving cyber threats that can compromise safety, privacy, data integrity, and service continuity. Conventional static defenses are often inadequate because they cannot autonomously adapt to changing attack behaviors or multi-stage intrusion patterns. This paper proposes Communication Aware Quantum Inspired Reinforcement Learning (CA-QIRL) framework built on a lightweight deep Q-Network architecture for next-generation autonomous cyber defense. V2X defense is formulated as a communication-aware Markov Decision Process (MDP), with the agent observing intrusion, mobility, Road Side Unit (RSU), and communication metrics, followed by selecting mitigation actions. CA-QIRL combines quantuminspired encoding, rotation exploration, interference reward, and cost function penalising false negatives, false positives, delay, packet loss, and RSU overload. Experimental evaluation on vehicular intrusion datasets (Car-Hacking, ROAD, VeReMi, CAN-MIRGU) and a mobilityaware V2X simulation demonstrates that the proposed framework achieves competitive detection accuracy of 97.89% on CICIDS2017 and 80.31% on CAN-MIRGU, while outperforming stateof-the-art ensemble methods in inference latency by factors of 69.2 times and 33.0 times, respectively. Moreover, the end-to-end delay and Channel Busy Ratio (CBR) are reduced by up to 95.7% and 90%, respectively, all while maintaining sub-100 􀀖s inference latency across all datasets. Furthermore, statistical significance is demonstrated on ROAD (Recall: 0.985 vs. 0.951, 􀁰 < 0.01) and VeReMi (Recall: 0.626 vs. 0.074, 􀁰 < 0.01) . These results suggest that Communication-Aware CA-QIRL is a practical cyber-resilient defense mechanism for nextgeneration V2X and Internet-of-Vehicles networks. [ cs .CR] arXiv :2606 .07804v2 1. Introduction Smart cities is a new paradigm for urban management. It integrate a diverse network of IoT and edge devices to optimize critical services. These include traffic control, energy systems, and public safety infrastructure. The IoV extends this ecosystem through intelligent and connected transportation systems. Unlike static smart city infrastructure, vehicular networks introduce unique vulnerabilities. These are stemming from high node mobility, heterogeneous communication protocols, and ephemeral network topologies. These factors change as vehicles traverse different coverage zones. More critically, any defensive response in autonomous vehicle systems must operate within submillisecond safety windows. Therefore, this delayed threat detection directly translates to physical harm through compromised braking, steering, and collision avoidance systems. These dense and highly interconnected environments expose a wide attack surface to sophisticated cyber threats. Moreover, they face multi-stage attack campaigns that evolve dynamically over time. Traditional static defense systems are designed around fixed sig

FAQs

Which performance aspects does the framework aim to improve?

The framework targets detection accuracy while reducing end-to-end delay and channel congestion (CBR). It also uses a cost function that penalizes false negatives, false positives, delay, packet loss, and RSU overload to maintain practical deployment behavior on edge systems.

Jul 16, 2026

Upload by Patrick