用硬件水印保护大模型生成的RTL代码版权，防抄袭更有效。
RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
- 基于规则的Verilog变换实现水印嵌入，保持代码正确性。
- 在合成网表中嵌入水印，提升版权保护效果。
- 平衡透明性与有效性，适合芯片设计版权保护场景。
大型语言模型在Verilog生成领域的进展引发了代码版权保护和恶意代码传播等伦理与安全问题。现有水印技术难以保护RTL代码，因其与Python等软件代码存在显著的语法和语义差异。本文提出硬件水印框架RTLMarker，将水印嵌入RTL代码及合成后的网表中。通过一系列基于规则的Verilog代码变换，确保水印后代码的语法与语义正确性。同时，考虑水印透明性与有效性之间的固有权衡，进行联合优化。实验表明，RTLMarker在RTL代码水印方面优于基线方法。
原文摘要 · Abstract (English)
Recent advances of large language models in the field of Verilog generation have raised several ethical and security concerns, such as code copyright protection and dissemination of malicious code. Researchers have employed watermarking techniques to identify codes generated by large language models. However, the existing watermarking works fail to protect RTL code copyright due to the significant syntactic and semantic differences between RTL code and software code in languages such as Python. This paper proposes a hardware watermarking framework RTLMarker that embeds watermarks into RTL code and deeper into the synthesized netlist. We propose a set of rule-based Verilog code transformations , ensuring the watermarked RTL code's syntactic and semantic correctness. In addition, we consider an inherent tradeoff between watermark transparency and watermark effectiveness and jointly optimize them. The results demonstrate RTLMarker's superiority over the baseline in RTL code watermarking.
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。