2026
CREDID: CREDIBLE MULTI-BIT WATERMARK FOR LARGE LANGUAGE MODELS IDENTIFICATION
ICASSP 2026poster
Large Language Models (LLMs) are widely used in complex natural language processing tasks but raise privacy and security concerns due to the lack of identity recognition. This paper proposes a multi-party credible watermarking framework (CredID) involving a trusted third party (TTP) and multiple LLM…