RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation

S. Skorobogatov et al. , “Breakthrough silicon scanning discovers backdoor in military chip,” in Proceedings of the 14th International Conference on Cryptographic Hardware and Embedded Systems , ser. CHES’12, 2012, p. 23–40

2012

Earlier work this paper cites.

M. Rostami et al. , “A primer on hardware security: Models, methods, and metrics,” Proceedings of the IEEE , vol. 102, no. 8, pp. 1283–1295, 2014

2014

Earlier work this paper cites.

K. Yang et al. , “A2: Analog malicious hardware,” in 2016 IEEE Symposium on Security and Privacy (SP) , 2016, pp. 18–37

2016

Earlier work this paper cites.

R. Schuster et al. , “You autocomplete me: Poisoning vulnerabilities in neural code completion,” in 30th USENIX Security Symposium (USENIX Security 21) . USENIX Association, Aug. 2021, pp. 1559–1575

2021

Earlier work this paper cites.

T. Trippel et al. , “Bomberman: Defining and defeating hardware ticking timebombs at design-time,” in 2021 IEEE Symposium on Security and Privacy (SP) , 2021, pp. 970–986

2021

Earlier work this paper cites.

J. Knechtel, “Hardware security for and beyond CMOS technology,” in Proc. Int. Symp. Phys. Des. , 2021

2021

Earlier work this paper cites.

S. Thakur et al. , “Verigen: A large language model for verilog code generation,” ACM TODAES , 2023

2023

Earlier work this paper cites.

S. Thakur et al. , “Autochip: Automating hdl generation using llm feedback,” arXiv preprint arXiv:2311.04887 , 2023

Original

2023

Earlier work this paper cites.

J. Blocklove et al. , “Chip-chat: Challenges and opportunities in conversational hardware design,” in 2023 ACM/IEEE 5th Workshop on Machine Learning for CAD (MLCAD) . IEEE, Sep. 2023

2023

Earlier work this paper cites.

M. Liu et al. , “Verilogeval: Evaluating large language models for verilog code generation,” in 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD) . IEEE, 2023, pp. 1–8

2023

Earlier work this paper cites.

R. Kande et al. , “Llm-assisted generation of hardware assertions,” arXiv preprint arXiv:2306.14027 , 2023

Original

2023

Earlier work this paper cites.

M. Liu et al. , “Chipnemo: Domain-adapted llms for chip design,” arXiv preprint arXiv:2311.00176 , 2023

Original

2023

Earlier work this paper cites.

E. Nijkamp et al. , “Codegen: An open large language model for code with multi-turn program synthesis,” 2023. [Online]. Available: https://arxiv.org/abs/2203.13474

Original

2023

Cited alongside, same era.

H. Touvron et al. , “Llama 2: Open foundation and fine-tuned chat models,” 2023. [Online]. Available: https://arxiv.org/abs/2307.09288

Original

2023

Cited alongside, same era.

Y. Fu et al. , “Gpt4aigchip: Towards next-generation ai accelerator design automation via large language models,” in 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD) . IEEE, 2023, pp. 1–9

2023

Cited alongside, same era.

K. Chang et al. , “Chipgpt: How far are we from natural language hardware design,” arXiv preprint arXiv:2305.14019 , 2023

Original

2023

Cited alongside, same era.

H. Aghakhani et al. , “Trojanpuzzle: Covertly poisoning code-suggestion models,” 2024. [Online]. Available: https://arxiv.org/abs/2301.02344

Original

2024

Closest in time.

H. Yang et al. , “A comprehensive overview of backdoor attacks in large language models within communication networks,” IEEE Network , pp. 1–1, 2024

2024

Closest in time.

S. Yan et al. , “An LLM-Assisted Easy-to-Trigger backdoor attack on code completion models: Injecting disguised vulnerabilities against strong detection,” in 33rd USENIX Security Symposium (USENIX Security 24) . Philadelphia, PA: USENIX Association, Aug. 2024, pp. 1795–1812

2024

Closest in time.

R. Zhang et al. , “Instruction backdoor attacks against customized LLMs,” in 33rd USENIX Security Symposium (USENIX Security 24) . Philadelphia, PA: USENIX Association, Aug. 2024, pp. 1849–1866. [Online]. Available: https://www.usenix.org/conference/usenixsecurity24/presentation/zhang-rui

2024