RTLMarker：通过硬件水印框架保护 LLM 生成的 RTL 版权
RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
AI总结：
针对 LLM 生成 RTL 的版权保护问题，本文提出 RTLMarker 框架，通过基于规则的 Verilog 转换将水印嵌入代码及综合网表，并联合优化透明性与有效性。
摘要：
大语言模型在 Verilog 生成领域的最新进展引发了若干伦理与安全问题，例如代码版权保护和恶意代码传播。研究人员已采用水印技术来识别大语言模型生成的代码。然而，由于 RTL 代码与 Python 等语言的软件代码在语法和语义上存在显著差异，现有水印工作无法保护 RTL 代码版权。本文提出硬件水印框架 RTLMarker，将水印嵌入 RTL 代码，并进一步深入到综合后的网表中。我们提出一组基于规则的 Verilog 代码转换，确保带水印 RTL 代码在语法和语义上的正确性。此外，我们考虑水印透明性与水印有效性之间固有的权衡，并对二者进行联合优化。结果表明，RTLMarker 在 RTL 代码水印方面优于基线。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
