RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917884228272128 |
|---|---|
| author | Wang, Kun Chang, Kaiyan Wang, Mengdi Zou, Xinqi Xu, Haobo Han, Yinhe Wang, Ying |
| author_facet | Wang, Kun Chang, Kaiyan Wang, Mengdi Zou, Xinqi Xu, Haobo Han, Yinhe Wang, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02446 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework Wang, Kun Chang, Kaiyan Wang, Mengdi Zou, Xinqi Xu, Haobo Han, Yinhe Wang, Ying Cryptography and Security Artificial Intelligence 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. |
| title | RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2501.02446 |