Skip to content
conftrace_
2025 ICML ICML 2025

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Yixin Cheng, Hongcheng Guo, Yangming Li, Leonid Sigal

Topics

Machine Learning > Learning Types > Adversarial Learning Natural Language Processing > Generation > Language Modeling Artificial Intelligence > Core AI > Large Language Models

Keywords

robustness text watermarking paraphrasing attack llm sampling self-information sira
Download PDF