paperApril 2026Unreviewed

HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking

Zeng Wang, Minghao Shao, Weimin Fu, Prithwish Basu Roy, Xiaolong Guo, Ramesh Karri, Muhammad Shafique, J. Knechtel, Ozgur Sinanoglu

arXiv.org

View resource

Abstract

The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns. Malicious LLM outputs in this domain pose hardware-level threats, including hardware Trojan insertion, side-channel leakage, and intellectual property theft, that are irreversible once fabricated into silicon. Such requests often exploit semantic disguise, embed

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection
LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data
AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{wang2026harmchip,
  title = {{HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking}},
  author = {Zeng Wang and Minghao Shao and Weimin Fu and Prithwish Basu Roy and Xiaolong Guo and Ramesh Karri and Muhammad Shafique and J. Knechtel and Ozgur Sinanoglu},
  year = {2026},
  month = apr,
  eprint = {2604.17093},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2604.17093},
  url = {https://www.semanticscholar.org/paper/b07fe49a982822288e33ad3f00b426553622bb8a}
}