Search papers, labs, and topics across Lattice.
VeriChat is a specialized conversational AI assistant designed to enhance hardware security verification by providing context-aware guidance throughout the verification process. By employing a retrieval-augmented, multi-agent workflow, it minimizes hallucinations and increases the reliability of responses, significantly outperforming leading proprietary models with a Faithfulness score of 87.73%. In a case study, VeriChat successfully identified and proved a covert key-leakage vulnerability in an AES S-Box IP, showcasing its practical application in real-world scenarios.
VeriChat achieves an impressive 87.73% Faithfulness score, dramatically reducing hallucinations in hardware security verification tasks.
Hardware security verification is a multi-stage process in which engineers must navigate complex design analyses, threat considerations, and verification strategies. They often need security-focused guidance, yet current verification environments provide little structured support for such assistance. Although conversational AI could offer such on-demand assistance, directly using general-purpose chatbots like ChatGPT or Gemini is risky due to their tendency to hallucinate and their reliance on static, outdated knowledge. We present VeriChat, a domain-specialized conversational assistant designed to support, rather than replace, existing verification workflows by providing context-aware security guidance. VeriChat employs a retrieval-augmented, multi-agent workflow in which three specialized agents collaboratively minimize hallucinations while improving the transparency and reliability of the response. Beyond question answering, VeriChat integrates open-source EDA tools, including Icarus Verilog, Yosys, and SymbiYosys, to perform syntax checking, synthesis analysis, simulation, and formal verification directly on user-provided RTL designs. Evaluated using a comprehensive methodology, VeriChat achieves a Faithfulness score of 87.73%, significantly outperforming the leading proprietary models. We demonstrate the framework through a hardware Trojan detection case study on an AES S-Box IP, where VeriChat autonomously identifies, simulates, and formally proves a covert key-leakage vulnerability through a multi-turn conversational workflow.
