RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework

TL;DR

RTLMarker is a novel hardware watermarking framework that embeds watermarks into RTL code and netlists, ensuring copyright protection for LLM-generated hardware designs while maintaining code correctness and optimizing watermark effectiveness.

Contribution

The paper introduces RTLMarker, a rule-based Verilog transformation framework that embeds watermarks into RTL code and netlists, addressing the limitations of existing software-focused watermarking techniques.

Findings

RTLMarker outperforms baseline methods in watermarking effectiveness.

The framework maintains syntactic and semantic correctness of RTL code.

It optimizes the tradeoff between watermark transparency and effectiveness.

Abstract

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.