Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging (2401.16448v1)

Published 28 Jan 2024 in cs.AR and cs.AI

Abstract: This paper presents LLM4SecHW, a novel framework for hardware debugging that leverages domain specific LLM. Despite the success of LLMs in automating various software development tasks, their application in the hardware security domain has been limited due to the constraints of commercial LLMs and the scarcity of domain specific data. To address these challenges, we propose a unique approach to compile a dataset of open source hardware design defects and their remediation steps, utilizing version control data. This dataset provides a substantial foundation for training machine learning models for hardware. LLM4SecHW employs fine tuning of medium sized LLMs based on this dataset, enabling the identification and rectification of bugs in hardware designs. This pioneering approach offers a reference workflow for the application of fine tuning domain specific LLMs in other research areas. We evaluate the performance of our proposed system on various open source hardware designs, demonstrating its efficacy in accurately identifying and correcting defects. Our work brings a new perspective on automating the quality control process in hardware design.

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. S. Ray, E. Peeters, M. M. Tehranipoor, and S. Bhunia, “System-on-chip platform security assurance: Architecture and validation,” Proceedings of the IEEE, vol. 106, no. 1, pp. 21–37, 2017.
  2. S. Aftabjahani, R. Kastner, M. Tehranipoor, F. Farahmandi, J. Oberg, A. Nordstrom, N. Fern, and A. Althoff, “Special session: Cad for hardware security-automation is key to adoption of solutions,” in 2021 IEEE 39th VLSI Test Symposium (VTS).   IEEE, 2021, pp. 1–10.
  3. M. L. King, “Practical security validation,” in 2013 14th International Workshop on Microprocessor Test and Verification, 2013, pp. 35–38.
  4. W. Xiong and J. Szefer, “Survey of transient execution attacks and their mitigations,” ACM Computing Surveys (CSUR), vol. 54, no. 3, pp. 1–36, 2021.
  5. K. Singhal, T. Tu, J. Gottweis, R. Sayres, E. Wulczyn, L. Hou, K. Clark, S. Pfohl, H. Cole-Lewis, D. Neal et al., “Towards expert-level medical question answering with large language models,” arXiv preprint arXiv:2305.09617, 2023.
  6. “Github copilot,” 2023. [Online]. Available: https://copilot.github.com/
  7. “Chatgpt based on gpt-4.” [Online]. Available: https://www.openai.com/
  8. M. Cosler, C. Hahn, D. Mendoza, F. Schmitt, and C. Trippel, “nl2spec: Interactively translating unstructured natural language to temporal logics with large language models,” 34th International Conference on Computer Aided Verification, July 2023.
  9. C. Sun, C. Hahn, and C. Trippel, “Towards improving verification productivity with circuit-aware translation of natural language to systemverilog assertions,” in First International Workshop on Deep Learning-aided Verification, 2023.
  10. R. Kande, H. Pearce, B. Tan, B. Dolan-Gavitt, S. Thakur, R. Karri, and J. Rajendran, “Llm-assisted generation of hardware assertions,” arXiv preprint arXiv:2306.14027, 2023.
  11. M. Gurman, “Samsung bans staff’s ai use after spotting chatgpt data leak,” Bloomberg News, vol. 2, 2023.
  12. Z. Jiang, E. Songhori, S. Wang, A. Goldie, A. Mirhoseini, J. Jiang, Y.-J. Lee, and D. Z. Pan, “Delving into macro placement with reinforcement learning,” in 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD (MLCAD).   IEEE, 2021, pp. 1–3.
  13. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
  14. M. Nair, R. Sadhukhan, and D. Mukhopadhyay, “Generating secure hardware using chatgpt resistant to cwes,” CSCML 2023, p. 320–336, 2023.
  15. S. Thakur, B. Ahmad, Z. Fan, H. Pearce, B. Tan, R. Karri, B. Dolan-Gavitt, and S. Garg, “Benchmarking large language models for automated verilog rtl code generation,” in 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE).   IEEE, 2023, pp. 1–6.
  16. B. Ahmad, S. Thakur, B. Tan, R. Karri, and H. Pearce, “Fixing hardware security bugs with large language models,” arXiv preprint arXiv:2302.01215, 2023.
  17. C.-K. Cheng, A. B. Kahng, S. Kundu, Y. Wang, and Z. Wang, “Assessment of reinforcement learning for macro placement,” in Proceedings of the 2023 International Symposium on Physical Design, ser. ISPD ’23.   New York, NY, USA: Association for Computing Machinery, 2023, p. 158–166. [Online]. Available: https://doi.org/10.1145/3569052.3578926
  18. S. Thakur, B. Ahmad, Z. Fan, H. Pearce, B. Tan, R. Karri, B. Dolan-Gavitt, and S. Garg, “Benchmarking large language models for automated verilog rtl code generation,” 2022. [Online]. Available: https://arxiv.org/abs/2212.11140
  19. F. Zaruba and L. Benini, “The cost of application-class processing: Energy and performance analysis of a linux-ready 1.7-ghz 64-bit risc-v core in 22-nm fdsoi technology,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 27, no. 11, pp. 2629–2640, Nov 2019.
  20. E. Matthews and L. Shannon, “Taiga: A new risc-v soft-processor framework enabling high performance cpu architectural features,” in 2017 27th International Conference on Field Programmable Logic and Applications (FPL), 2017, pp. 1–4.
  21. S. Johnson, D. Rizzo, P. Ranganathan, J. McCune, and R. Ho, “Titan: enabling a transparent silicon root of trust for cloud,” in Hot Chips: A Symposium on High Performance Chips, vol. 194, 2018, p. 10.
  22. P. D. Schiavone, F. Conti, D. Rossi, M. Gautschi, A. Pullini, E. Flamand, and L. Benini, “Slow and steady wins the race? a comparison of ultra-low-power risc-v cores for internet-of-things applications,” in 2017 27th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS).   IEEE, 2017, pp. 1–8.
  23. Stafford Horne, “mor1kx,” https://github.com/openrisc/mor1kx.
  24. J. Balkind, M. McKeown, Y. Fu, T. Nguyen, Y. Zhou, A. Lavrov, M. Shahrad, A. Fuchs, S. Payne, X. Liang, M. Matl, and D. Wentzlaff, “OpenPiton: An Open Source Manycore Research Framework,” in Proceedings of the Twenty-First International Conference on Architectural Support for Programming Languages and Operating Systems, ser. ASPLOS ’16.   New York, NY, USA: ACM, 2016, pp. 217–232, event-place: Atlanta, Georgia, USA. [Online]. Available: http://doi.acm.org/10.1145/2872362.2872414
  25. A. Pullini, D. Rossi, I. Loi, G. Tagliavini, and L. Benini, “Mr.wolf: An energy-precision scalable parallel ultra low power soc for iot edge processing,” IEEE Journal of Solid-State Circuits, vol. 54, no. 7, pp. 1970–1981, 2019.
  26. Darklife, “Darkriscv,” https://github.com/darklife/darkriscv.
  27. M. Allamanis, “The adverse effects of code duplication in machine learning models of code,” in Proceedings of the 2019 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software, 2019, pp. 143–153.
  28. “Verilator,” 2023. [Online]. Available: https://veripool.org/verilator/
  29. I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in International Conference on Learning Representations, 2019. [Online]. Available: https://openreview.net/forum?id=Bkg6RiCqY7
  30. A. Andonian, Q. Anthony, S. Biderman, S. Black, P. Gali, L. Gao, E. Hallahan, J. Levy-Kramer, C. Leahy, L. Nestler, K. Parker, M. Pieler, S. Purohit, T. Songz, W. Phil, and S. Weinbach, “GPT-NeoX: Large Scale Autoregressive Language Modeling in PyTorch,” 8 2021. [Online]. Available: https://www.github.com/eleutherai/gpt-neox
  31. E. Almazrouei, H. Alobeidli, A. Alshamsi, A. Cappelli, R. Cojocaru, M. Debbah, E. Goffinet, D. Heslow, J. Launay, Q. Malartic, B. Noune, B. Pannier, and G. Penedo, “Falcon-40B: an open large language model with state-of-the-art performance,” 2023.
  32. D. Park, “Open-llm-leaderboard-report,” 2023. [Online]. Available: https://github.com/dsdanielpark/Open-LLM-Leaderboard-Report
  33. H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar et al., “Llama: Open and efficient foundation language models,” arXiv preprint arXiv:2302.13971, 2023.
  34. Bard, “Bard: A large language model from google ai,” 2023. [Online]. Available: https://bard.ai
  35. OpenAI, “Gpt-4 technical report,” 2023.
  36. P. Gao, J. Han, R. Zhang, Z. Lin, S. Geng, A. Zhou, W. Zhang, P. Lu, C. He, X. Yue, H. Li, and Y. Qiao, “Llama-adapter v2: Parameter-efficient visual instruction model,” 2023.
  37. C.-Y. Lin, “Rouge: A package for automatic evaluation of summaries,” in Text summarization branches out, 2004, pp. 74–81.
  38. Y. Zhao, A. Gu, R. Varma, L. Luo, C.-C. Huang, M. Xu, L. Wright, H. Shojanazeri, M. Ott, S. Shleifer, A. Desmaison, C. Balioglu, B. Nguyen, G. Chauhan, Y. Hao, and S. Li, “Pytorch fsdp: Experiences on scaling fully sharded data parallel,” 2023.
  39. “Opentitan,” https://opentitan/hw/dv/dpi/jtagdpi/jtagdpi.sv.
  40. D. A. S. Committee et al., “Ieee standard for systemverilog–unified hardware design, specification, and verification language,” IEEE Std 1800-2017 (Revision of IEEE Std 1800-2012), pp. 1–1315, 2018.
  41. “OpenTitan,” https://opentitan.org/.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Weimin Fu (3 papers)
  2. Kaichen Yang (2 papers)
  3. Raj Gautam Dutta (2 papers)
  4. Xiaolong Guo (8 papers)
  5. Gang Qu (40 papers)
Citations (17)
View on Semantic Scholar

Summary

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

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