Reinforcement learning in VANET penetration testing
The recent popularity of Connected and Autonomous Vehicles (CAV) corresponds with an increase in the risk of cyber-attacks. These cyber-attacks are instigated by white-coat hackers, and cyber-criminals. As Connected Vehicles move towards full autonomy the impact of these cyber-attacks also grows. Th...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-03-01
|
Series: | Results in Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S259012302300097X |
_version_ | 1797895541809479680 |
---|---|
author | Phillip Garrad Saritha Unnikrishnan |
author_facet | Phillip Garrad Saritha Unnikrishnan |
author_sort | Phillip Garrad |
collection | DOAJ |
description | The recent popularity of Connected and Autonomous Vehicles (CAV) corresponds with an increase in the risk of cyber-attacks. These cyber-attacks are instigated by white-coat hackers, and cyber-criminals. As Connected Vehicles move towards full autonomy the impact of these cyber-attacks also grows. The current research highlights challenges faced in cybersecurity testing of CAV, including access, the cost of representative test setup and the 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 Reinforcement Learning model, called Q-Learning, is applied to automate the software simulation. The expectation from this implementation is to see improvements in runtime and efficiency for the VANET model. The results show this approach to be promising 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. |
first_indexed | 2024-04-10T07:27:26Z |
format | Article |
id | doaj.art-5795132911ce470c8ce353e817e733be |
institution | Directory Open Access Journal |
issn | 2590-1230 |
language | English |
last_indexed | 2024-04-10T07:27:26Z |
publishDate | 2023-03-01 |
publisher | Elsevier |
record_format | Article |
series | Results in Engineering |
spelling | doaj.art-5795132911ce470c8ce353e817e733be2023-02-24T04:31:36ZengElsevierResults in Engineering2590-12302023-03-0117100970Reinforcement learning in VANET penetration testingPhillip Garrad0Saritha Unnikrishnan1Faculty of Engineering & Design, Atlantic Technological University (ATU) Sligo, Ireland; Corresponding author.Faculty of Engineering & Design, Atlantic Technological University (ATU) Sligo, Ireland; Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), ATU Sligo, Ireland; Corresponding author. Faculty of Engineering & Design, Atlantic Technological University (ATU), Sligo, Ireland.The recent popularity of Connected and Autonomous Vehicles (CAV) corresponds with an increase in the risk of cyber-attacks. These cyber-attacks are instigated by white-coat hackers, and cyber-criminals. As Connected Vehicles move towards full autonomy the impact of these cyber-attacks also grows. The current research highlights challenges faced in cybersecurity testing of CAV, including access, the cost of representative test setup and the 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 Reinforcement Learning model, called Q-Learning, is applied to automate the software simulation. The expectation from this implementation is to see improvements in runtime and efficiency for the VANET model. The results show this approach to be promising 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.http://www.sciencedirect.com/science/article/pii/S259012302300097XCybersecurityConnected vehiclesSoftware simulationArtificial intelligencePenetration testing |
spellingShingle | Phillip Garrad Saritha Unnikrishnan Reinforcement learning in VANET penetration testing Results in Engineering Cybersecurity Connected vehicles Software simulation Artificial intelligence Penetration testing |
title | Reinforcement learning in VANET penetration testing |
title_full | Reinforcement learning in VANET penetration testing |
title_fullStr | Reinforcement learning in VANET penetration testing |
title_full_unstemmed | Reinforcement learning in VANET penetration testing |
title_short | Reinforcement learning in VANET penetration testing |
title_sort | reinforcement learning in vanet penetration testing |
topic | Cybersecurity Connected vehicles Software simulation Artificial intelligence Penetration testing |
url | http://www.sciencedirect.com/science/article/pii/S259012302300097X |
work_keys_str_mv | AT phillipgarrad reinforcementlearninginvanetpenetrationtesting AT sarithaunnikrishnan reinforcementlearninginvanetpenetrationtesting |