Reinforcement Learning in VANET Penetration Testing /

Abstract

The recent popularity of Connected and Autonomous Vehicles (CAV) corresponds with an increase in the risk of cyber-attacks. These cyber-attacks have been instigated by both researchers or white-coat hackers, and cyber-criminals. As Connected Vehicles move towards full autonomy the impact of these cyber-attacks also grows. The current research details challenges faced in cybersecurity testing of CAV, including access and the cost of representative test setup. Other challenges faced are lack of experts in the field. Possible solutions of how these challenges can be overcome are reviewed and discussed. From these findings a software simulated Vehicular Ad Hoc NETwork (VANET) is established as a cost effective representative testbed. Penetration tests are then performed on this simulation, demonstrating a cyber-attack in CAV. Studies have shown Artificial Intelligence (AI) to improve runtime, increase efficiency and comprehensively cover all the typical test aspects, in penetration testing in other industries. In this research a similar AI Reinforcement Learning model, Q-Learning, is applied to the software simulation. The expectation from this implementation is to see similar improvements in runtime and efficiency for the VANET model. The results show this to be true and using AI in penetration testing for VANET to improve efficiency in most cases. Each case is reviewed in detail before discussing possible ways to improve the implementation and get a truer reflection of the real-world application.