StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
By: Ya Jiang , Chuxiong Wu , Massieh Kordi Boroujeny and more
Potential Business Impact:
Marks AI writing so you know who wrote it.
Watermarking for large language models (LLMs) offers a promising approach to identifying AI-generated text. Existing approaches, however, either compromise the distribution of original generated text by LLMs or are limited to embedding zero-bit information that only allows for watermark detection but ignores identification. We present StealthInk, a stealthy multi-bit watermarking scheme that preserves the original text distribution while enabling the embedding of provenance data, such as userID, TimeStamp, and modelID, within LLM-generated text. This enhances fast traceability without requiring access to the language model's API or prompts. We derive a lower bound on the number of tokens necessary for watermark detection at a fixed equal error rate, which provides insights on how to enhance the capacity. Comprehensive empirical evaluations across diverse tasks highlight the stealthiness, detectability, and resilience of StealthInk, establishing it as an effective solution for LLM watermarking applications.
Similar Papers
Invariant-based Robust Weights Watermark for Large Language Models
Cryptography and Security
Protects computer programs from being copied.
DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Models
Cryptography and Security
Tracks who made and shared AI text.
EditMark: Watermarking Large Language Models based on Model Editing
Cryptography and Security
Marks AI writing to prove it's yours.