paper-with-me

Papers

MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages

2026-02-15 · Xuehao Cui, Ruibo Chen, Yihan Wu, Heng Huang arxiv

Large language models now produce text indistinguishable from human writing, which increases the need for reliable provenance tracing. Multi-bit watermarking can embed identifiers into generated text, but existing methods struggle to keep both text quality and watermark strength while carrying long messages. We propose MC$^2$Mark, a distortion-free multi-bit watermarking framework designed for reliable embedding and decoding of long messages. Our key technical idea is Multi-Channel Colored Reweighting, which encodes bits through structured token reweighting while keeping the token distribution unbiased, together with Multi-Layer Sequential Reweighting to strengthen the watermark signal and an evidence-accumulation detector for message recovery. Experiments show that MC$^2$Mark improves detectability and robustness over prior multi-bit watermarking methods while preserving generation quality, achieving near-perfect accuracy for short messages and exceeding the second-best method by nearly 30% for long messages.

📄 PDF Abstract BibTeX arXiv:2602.14030

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multi-Bit Distortion-Free Watermarking for Large Language Models

2024-02-26 · Massieh Kordi Boroujeny, Ya Jiang, Kai Zeng, Brian Mark

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the …

Decoder

Adversarial Shallow Watermarking

2025-04-28 · Guobiao Li, Lei Tan, Yuliang Xue, Gaozhi Liu 외

Recent advances in digital watermarking make use of deep neural networks for message embedding and extraction. They typically follow the ``encoder-noise layer-decoder''-based architecture. By deliberately establishing a …

Decoder

Breaking Distortion-free Watermarks in Large Language Models

2025-02-25 · Shayleen Reynolds, Hengzhi He, Dung Daniel T. Ngo, Saheed Obitayo 외

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM wate…

ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport

2026-02-06 · Atefeh Gilani, Sajani Vithana, Carol Xuan Long, Oliver Kosut 외 arxiv

Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM-generated text (zero-bit watermarking) …

Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions

2024-06-02 · Yihan Wu, Ruibo Chen, Zhengmian Hu, Yanshuo Chen 외

Language model (LM) watermarking techniques inject a statistical signal into LM-generated content by substituting the random sampling process with pseudo-random sampling, using watermark keys as the random seed. Among th…

Language ModelingLanguage Modelling