用机器遗忘技术清除LLM中的敏感硬件代码，保障设计安全
SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
- 通过机器遗忘技术移除污染数据和恶意代码模式
- 无需重训练即可清除敏感知识产权和设计资产
- 适合关注LLM硬件设计安全的工程师与研究人员
大型语言模型（LLMs）在硬件设计自动化中具有变革性潜力，尤其在Verilog代码生成方面。然而，它们也带来显著的数据安全挑战，包括Verilog评估数据污染、知识产权（IP）设计泄露以及恶意Verilog生成风险。本文提出SALAD，一种全面评估框架，利用机器遗忘技术缓解这些威胁。该方法可选择性地从预训练LLM中移除受污染基准、敏感IP及设计内容或恶意代码模式，且无需完整重新训练。通过详细案例研究，验证了机器遗忘技术在降低LLM辅助硬件设计中的数据安全风险方面的有效性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。