Vol. 1 No. 1 (2021): Journal of AI-Assisted Scientific Discovery
Articles

Deep Reinforcement Learning for Adaptive Cyber Defense in IoT-connected Autonomous Vehicle Networks

PDF
  • Dr. Olga Volkova
Dr. Olga Volkova
Professor of Artificial Intelligence, National Research University – Information Technologies, Mechanics and Optics (ITMO)
Cover

Published 30-06-2021

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

How to Cite

[1]
Dr. Olga Volkova, “Deep Reinforcement Learning for Adaptive Cyber Defense in IoT-connected Autonomous Vehicle Networks”, Journal of AI-Assisted Scientific Discovery, vol. 1, no. 1, pp. 30–49, Jun. 2021, Accessed: Sep. 16, 2024. [Online]. Available: https://scienceacadpress.com/index.php/jaasd/article/view/62

Abstract

In particular, the novel cyber defence mechanism is based on a robust, Reinforcement Learning-based Intrusion Detection & Response (RLIDR) module, which receives encrypted Low-Level Telemetry & Control (LLT&C) data streams and has an interface with a Human-Machine Interface (HMI). The architecture is based on Long Short-Term Memory (LSTM) recurrent neural network and convolutional layers, useful to understand waveforms and other hidden and non-linear information. LSTM is useful in the detection mechanisms because it can process the incoming LLT&C data stream, monitoring latency, signal bitrate and deep messages sharing with respect to the classical sequence-to-sequence Terminator-Transformer model. Attack resistance properties are developed over time by having an adaptation phase to the network characteristics, and this means that a proper Reinforcement Learning (RL) algorithm was conceived and selected to adapt dynamic energy driven threat against the system, considering the different behavior of the threat found in time with respect to the vehicle dynamics. Finally, a simulation in a controlled IoT scenario is shown, based on real telecommunication data from the metropolitan area of the city of Milano, to give evidence that the proposed RLIDR is quite robust.

PDF

Downloads

Download data is not yet available.

References

  1. [1] R. Singh Rathore, C. Hewage, O. Kaiwartya, and J. Lloret, "In-Vehicle Communication Cyber Security: Challenges and Solutions," 2022. ncbi.nlm.nih.gov
  2. [2] S. K. B Sangeetha, P. Mani, V. Maheshwari, P. Jayagopal et al., "Design and Analysis of Multilayered Neural Network-Based Intrusion Detection System in the Internet of Things Network," 2022. ncbi.nlm.nih.gov
  3. [3] S. Mahadik, P. M. Pawar, and R. Muthalagu, "Efficient Intelligent Intrusion Detection System for Heterogeneous Internet of Things (HetIoT)," 2023. ncbi.nlm.nih.gov
  4. Mahammad Shaik, et al. “Envisioning Secure and Scalable Network Access Control: A Framework for Mitigating Device Heterogeneity and Network Complexity in Large-Scale Internet-of-Things (IoT) Deployments”. Distributed Learning and Broad Applications in Scientific Research, vol. 3, June 2017, pp. 1-24, https://dlabi.org/index.php/journal/article/view/1.
  5. Tatineni, Sumanth. "Beyond Accuracy: Understanding Model Performance on SQuAD 2.0 Challenges." International Journal of Advanced Research in Engineering and Technology (IJARET) 10.1 (2019): 566-581.
  6. Vemoori, V. “Towards Secure and Trustworthy Autonomous Vehicles: Leveraging Distributed Ledger Technology for Secure Communication and Exploring Explainable Artificial Intelligence for Robust Decision-Making and Comprehensive Testing”. Journal of Science & Technology, vol. 1, no. 1, Nov. 2020, pp. 130-7, https://thesciencebrigade.com/jst/article/view/224.
  7. [7] T. H. H. Aldhyani and H. Alkahtani, "Attacks to Automatous Vehicles: A Deep Learning Algorithm for Cybersecurity," 2022. ncbi.nlm.nih.gov
  8. [8] J. Egger, A. Pepe, C. Gsaxner, Y. Jin et al., "Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact," 2021. ncbi.nlm.nih.gov
  9. [9] Y. Wang, A. Smahi, H. Zhang, and H. Li, "Towards Double Defense Network Security Based on Multi-Identifier Network Architecture," 2022. ncbi.nlm.nih.gov
  10. [10] S. Oesch, P. Austria, A. Chaulagain, B. Weber et al., "The Path To Autonomous Cyber Defense," 2024. [PDF]
  11. [11] S. Ullah, M. A. Khan, J. Ahmad, S. Shaukat Jamal et al., "HDL-IDS: A Hybrid Deep Learning Architecture for Intrusion Detection in the Internet of Vehicles," 2022. ncbi.nlm.nih.gov
  12. [12] A. Demontis, M. Pintor, L. Demetrio, K. Grosse et al., "A Survey on Reinforcement Learning Security with Application to Autonomous Driving," 2022. [PDF]
  13. [13] N. Parvez Farazi, T. Ahamed, L. Barua, and B. Zou, "Deep Reinforcement Learning and Transportation Research: A Comprehensive Review," 2020. [PDF]
  14. [14] E. Bates, V. Mavroudis, and C. Hicks, "Reward Shaping for Happier Autonomous Cyber Security Agents," 2023. [PDF]
  15. [15] X. H. Nguyen, X. D. Nguyen, H. H. Huynh, and K. H. Le, "Realguard: A Lightweight Network Intrusion Detection System for IoT Gateways," 2022. ncbi.nlm.nih.gov
  16. [16] T. Thi Nguyen and V. Janapa Reddi, "Deep Reinforcement Learning for Cyber Security," 2019. [PDF]
  17. [17] P. Vaishno Mohan, S. Dixit, A. Gyaneshwar, U. Chadha et al., "Leveraging Computational Intelligence Techniques for Defensive Deception: A Review, Recent Advances, Open Problems and Future Directions," 2022. ncbi.nlm.nih.gov
  18. [18] M. Karkheiran, "Yukawa Textures From Singular Spectral Data," 2021. [PDF]
  19. [19] L. Yu, S. Huo, K. Li, and Y. Wei, "A Collision Relationship-Based Driving Behavior Decision-Making Method for an Intelligent Land Vehicle at a Disorderly Intersection via DRQN," 2022. ncbi.nlm.nih.gov
  20. [20] J. Mern, K. Hatch, R. Silva, J. Brush et al., "Reinforcement Learning for Industrial Control Network Cyber Security Orchestration," 2021. [PDF]
  21. [21] B. Ben Elallid, A. Abouaomar, N. Benamar, and A. Kobbane, "Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning," 2023. [PDF]
  22. [22] X. Xiong and L. Liu, "Combining Policy Gradient and Safety-Based Control for Autonomous Driving," 2023. [PDF]
  23. [23] H. Cao, W. Zou, Y. Wang, T. Song et al., "Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey," 2022. [PDF]
  24. [24] A. Uprety and D. B. Rawat, "Reinforcement Learning for IoT Security: A Comprehensive Survey," 2021. [PDF]
  25. [25] K. Istiaque Ahmed, M. Tahir, M. Hadi Habaebi, S. Lun Lau et al., "Machine Learning for Authentication and Authorization in IoT: Taxonomy, Challenges and Future Research Direction," 2021. ncbi.nlm.nih.gov
  26. [26] Y. Deng, T. Zhang, G. Lou, X. Zheng et al., "Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses," 2021. [PDF]
  27. [27] J. Wiebe, R. Al Mallah, and L. Li, "Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning," 2023. [PDF]
  28. [28] D. K. Galloway, J. J. M. in 't Zand, J. Chenevez, L. Keek et al., "The Influence of Stellar Spin on Ignition of Thermonuclear Runaways," 2018. [PDF]
  29. [29] A. Olivares-Del Campo, S. Palomares-Ruiz, and S. Pascoli, "Implications of a Dark Matter-Neutrino Coupling at Hyper-Kamiokande," 2018. [PDF]