![[2602.14030] MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.14030] MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages
Summary
MC$^2$Mark introduces a novel watermarking framework that ensures reliable embedding of long messages in generated text while maintaining quality, addressing the growing need for provenance tracing in AI-generated content.
Why It Matters
As large language models produce increasingly human-like text, the ability to trace the origin and authenticity of this content becomes crucial. MC$^2$Mark offers a solution to effectively embed identifiers without compromising text quality, enhancing content integrity in various applications.
Key Takeaways
- MC$^2$Mark utilizes Multi-Channel Colored Reweighting for effective watermarking.
- The framework maintains text quality while embedding long messages.
- Experiments show significant improvements in detectability and robustness over existing methods.
Computer Science > Cryptography and Security arXiv:2602.14030 (cs) [Submitted on 15 Feb 2026] Title:MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages Authors:Xuehao Cui, Ruibo Chen, Yihan Wu, Heng Huang View a PDF of the paper titled MC$^2$Mark: Distortion-Free Multi-Bit Watermarking for Long Messages, by Xuehao Cui and 3 other authors View PDF Abstract: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. Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2602.14030 ...
