RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
This addresses copyright protection for hardware designers using LLMs to generate RTL code, though it appears incremental as it adapts watermarking to a new domain.
The paper tackles the problem of protecting copyright for LLM-generated RTL code by proposing RTLMarker, a hardware watermarking framework that embeds watermarks into RTL code and synthesized netlists while maintaining correctness. The results show RTLMarker's superiority over baselines in RTL code watermarking.
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.