Newest papers

A Unified Attack Framework against Statistical Generative Watermarks for Large Language Models

Romina Omidi, Nima Naderloui, Yuan Hong, Binghui Wang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.27653 · open-access PDF

Hindi

वाटरमार्किंग बड़े भाषा मॉडल (एलएलएम) द्वारा उत्पन्न टेक्स्ट की पहचान के लिए एक महत्वपूर्ण उपकरण के रूप में उभरा है, वर्तमान योजनाओं के साथ उत्पन्न प्रक्रिया में सांख्यिकीय संकेतों को शामिल करने के लिए बाद में पता लगाने की अनुमति देने के लिए। इस काम में, हम KGW (और इसके रूपों), GumbelSoft, DipMark, ITS, और SynthID सहित लोकप्रिय एलएलएम वाटरमार्किंग विधियों के एक विस्तृत वर्ग में एक साझा कमजोरी की पहचान करते हैं।

Machine translation (Meta M2M100); the English original follows.

Abstract

Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical signals into the generation process to enable later detection. In this work, we identify a shared weakness across a broad class of popular LLM watermarking methods, including KGW (and its variants), GumbelSoft, DipMark, ITS, and SynthID. We show that these schemes exhibit a fundamental link between their detection scores and the token probability shifts they introduce during generation. This link, which we call score-ratio alignment, allows an attack

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27653, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange