New framework RoSeMary embeds secure watermarks in LLM-generated code

Researchers have developed RoSeMary, a novel framework for watermarking code generated by large language models. This system uses a combination of machine learning and cryptography to embed watermarks that can be securely verified without revealing the underlying signature, thus protecting intellectual property and preventing misuse. RoSeMary leverages a pre-trained CodeT5 model to ensure watermarked code maintains its functionality while enhancing detectability and robustness against various attacks. AI

IMPACT Enhances security and intellectual property protection for LLM-generated code, potentially impacting software development workflows.

RANK_REASON The item is a research paper detailing a new method for watermarking LLM-generated code. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• arXiv
• CatalyzeX
• CodeT5+
• DagsHub
• Gotit.pub
• Hugging Face
• RoSeMary
• Ruisi Zhang
• ScienceCast

• paper
• product
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →