Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Lightweight Multi-Attack CAN Intrusion Detection System on Hybrid FPGAs (2401.10689v1)

Published 19 Jan 2024 in cs.CR, cs.LG, cs.SY, and eess.SY

Abstract: Rising connectivity in vehicles is enabling new capabilities like connected autonomous driving and advanced driver assistance systems (ADAS) for improving the safety and reliability of next-generation vehicles. This increased access to in-vehicle functions compromises critical capabilities that use legacy invehicle networks like Controller Area Network (CAN), which has no inherent security or authentication mechanism. Intrusion detection and mitigation approaches, particularly using machine learning models, have shown promising results in detecting multiple attack vectors in CAN through their ability to generalise to new vectors. However, most deployments require dedicated computing units like GPUs to perform line-rate detection, consuming much higher power. In this paper, we present a lightweight multi-attack quantised machine learning model that is deployed using Xilinx's Deep Learning Processing Unit IP on a Zynq Ultrascale+ (XCZU3EG) FPGA, which is trained and validated using the public CAN Intrusion Detection dataset. The quantised model detects denial of service and fuzzing attacks with an accuracy of above 99 % and a false positive rate of 0.07%, which are comparable to the state-of-the-art techniques in the literature. The Intrusion Detection System (IDS) execution consumes just 2.0 W with software tasks running on the ECU and achieves a 25 % reduction in per-message processing latency over the state-of-the-art implementations. This deployment allows the ECU function to coexist with the IDS with minimal changes to the tasks, making it ideal for real-time IDS in in-vehicle systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. R. B. GmbH, “CAN Specification, Version 2.0,” 1991.
  2. F. Hartwich et al., “CAN with flexible data-rate,” in Proc. iCC, pp. 1–9, Citeseer, 2012.
  3. C. Miller and C. Valasek, “Remote exploitation of an unaltered passenger vehicle,” Black Hat USA, vol. 2015, no. S 91, 2015.
  4. M. Enev, A. Takakuwa, K. Koscher, and T. Kohno, “Automobile Driver Fingerprinting.,” Proc. Privacy Enhancing Technology, vol. 2016, no. 1, pp. 34–50, 2016.
  5. C.-W. Lin and A. Sangiovanni-Vincentelli, “Cyber-security for the controller area network (CAN) communication protocol,” in Proc. Intl. Conf. on Cyber Security, pp. 1–7, IEEE, 2012.
  6. K.-T. Cho and K. G. Shin, “Fingerprinting electronic control units for vehicle intrusion detection,” in USENIX Security Symposium (USENIX Security), pp. 911–927, 2016.
  7. K.-T. Cho and K. G. Shin, “Viden: Attacker identification on in-vehicle networks,” in Proc. Conf. on Computer and Communications Security, pp. 1109–1123, 2017.
  8. H. Lee, S. H. Jeong, and H. K. Kim, “OTIDS: A novel intrusion detection system for in-vehicle network by using remote frame,” in Proc. Conf. on Privacy, Security and Trust (PST), pp. 57–5709, IEEE, 2017.
  9. S. N. Narayanan, S. Mittal, and A. Joshi, “Using data analytics to detect anomalous states in vehicles,” arXiv preprint arXiv:1512.08048, 2015.
  10. A. Alshammari, M. A. Zohdy, D. Debnath, and G. Corser, “Classification approach for intrusion detection in vehicle systems,” Wireless Engineering and Technology, vol. 9, no. 4, pp. 79–94, 2018.
  11. L. Yang, A. Moubayed, I. Hamieh, and A. Shami, “Tree-based intelligent intrusion detection system in internet of vehicles,” in Proc. IEEE Global Communications Conference (GLOBECOM), pp. 1–6, IEEE, 2019.
  12. H. M. Song, J. Woo, and H. K. Kim, “In-vehicle network intrusion detection using deep convolutional neural network,” Vehicular Communications, vol. 21, p. 100198, 2020.
  13. S. Tariq, S. Lee, and S. S. Woo, “CANTransfer: transfer learning based intrusion detection on a controller area network using convolutional LSTM network,” in Proc. ACM Sym. on Applied Computing, pp. 1048–1055, 2020.
  14. E. Seo, H. M. Song, and H. K. Kim, “GIDS: GAN based intrusion detection system for in-vehicle network,” in Proc. Conf. on Privacy, Security and Trust (PST), pp. 1–6, IEEE, 2018.
  15. P. Cheng, K. Xu, S. Li, and M. Han, “TCAN-IDS: Intrusion Detection System for Internet of Vehicle Using Temporal Convolutional Attention Network,” Symmetry, vol. 14, no. 2, p. 310, 2022.
  16. K. Agrawal, T. Alladi, A. Agrawal, V. Chamola, and A. Benslimane, “NovelADS: A Novel Anomaly Detection System for Intra-Vehicular Networks,” IEEE Transactions on Intelligent Transportation Systems, 2022.
  17. L. Yang, A. Moubayed, and A. Shami, “MTH-IDS: A Multitiered Hybrid Intrusion Detection System for Internet of Vehicles,” IEEE Internet of Things Journal, vol. 9, no. 1, pp. 616–632, 2021.
  18. P. F. De Araujo-Filho, A. J. Pinheiro, G. Kaddoum, D. R. Campelo, and F. L. Soares, “An Efficient Intrusion Prevention System for CAN: Hindering Cyber-Attacks with a Low-Cost Platform,” IEEE Access, vol. 9, pp. 166855–166869, 2021.
  19. F. Fons and M. Fons, “FPGA-based automotive ECU design addresses AUTOSAR and ISO 26262 standards,” Xcell journal, vol. 78, p. 20, 2012.
  20. S. Shreejith and S. A. Fahmy, “Smart network interfaces for advanced automotive applications,” IEEE Micro, vol. 38, no. 2, pp. 72–80, 2018.
  21. Xilinx, “Vitis AI User Guide,” 2021.
  22. Y. Gorbachev, M. Fedorov, I. Slavutin, A. Tugarev, M. Fatekhov, and Y. Tarkan, “Openvino deep learning workbench: Comprehensive analysis and tuning of neural networks inference,” in Proc. Intl. Conf. on Computer Vision Workshops, pp. 0–0, 2019.
  23. E. Wang, J. J. Davis, P. Y. Cheung, and G. A. Constantinides, “LUTNet: Rethinking inference in FPGA soft logic,” in Proc. Intl. Sym. on Field-Programmable Custom Computing Machines (FCCM), pp. 26–34, IEEE, 2019.
  24. Y. Umuroglu, N. J. Fraser, G. Gambardella, M. Blott, P. Leong, M. Jahre, and K. Vissers, “Finn: A framework for fast, scalable binarized neural network inference,” in Proc. Intl. Sym. on Field-Programmable Gate Arrays (FPGA), pp. 65–74, 2017.
  25. S. Soltani, Y. E. Sagduyu, R. Hasan, K. Davaslioglu, H. Deng, and T. Erpek, “Real-time and embedded deep learning on FPGA for RF signal classification,” in Proc. IEEE Military Communications Conference (MILCOM), pp. 1–6, IEEE, 2019.
  26. H. Nakahara, M. Shimoda, and S. Sato, “A demonstration of FPGA-based you only look once version2 (YOLOv2),” in Proc. Intl. Conf. on Field Programmable Logic and Applications (FPL), pp. 457–4571, IEEE, 2018.
  27. D. Mahajan, J. Park, E. Amaro, H. Sharma, A. Yazdanbakhsh, J. K. Kim, and H. Esmaeilzadeh, “Tabla: A unified template-based framework for accelerating statistical machine learning,” in Proc. Intl. Sym. on High Performance Computer Architecture (HPCA), pp. 14–26, IEEE, 2016.
  28. Xilinx, “Zynq DPU v3.2,” 2020.
  29. CAR Hacking Dataset, “https://ocslab.hksecurity.net/datasets/can-intrusion-dataset,” 2020.
  30. S. Wu, G. Li, F. Chen, and L. Shi, “Training and inference with integers in deep neural networks,” arXiv preprint arXiv:1802.04680, 2018.
  31. A. K. Desta, S. Ohira, I. Arai, and K. Fujikawa, “MLIDS: Handling Raw High-Dimensional CAN Bus Data Using Long Short-Term Memory Networks for Intrusion Detection in In-Vehicle Networks,” in Proc. Intl. Telecommunication Networks and Applications Conference (ITNAC), pp. 1–7, IEEE, 2020.
Citations (10)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets