LGARCRMay 11, 2024

LLMs and the Future of Chip Design: Unveiling Security Risks and Building Trust

arXiv:2405.07061v138 citationsh-index: 22ISVLSI
Originality Synthesis-oriented
AI Analysis

This work identifies security and trust issues in using LxMs for chip design, which is crucial for the semiconductor industry and AI safety, but it is incremental as it builds on existing automation trends.

The paper addresses the integration of large language, multimodal, and circuit models (LxMs) into chip design, highlighting both the potential benefits and the emerging security risks, with initial answers provided for attack and defense perspectives.

Chip design is about to be revolutionized by the integration of large language, multimodal, and circuit models (collectively LxMs). While exploring this exciting frontier with tremendous potential, the community must also carefully consider the related security risks and the need for building trust into using LxMs for chip design. First, we review the recent surge of using LxMs for chip design in general. We cover state-of-the-art works for the automation of hardware description language code generation and for scripting and guidance of essential but cumbersome tasks for electronic design automation tools, e.g., design-space exploration, tuning, or designer training. Second, we raise and provide initial answers to novel research questions on critical issues for security and trustworthiness of LxM-powered chip design from both the attack and defense perspectives.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes