PulseAugur
EN
LIVE 07:38:08

New framework enables user attribution and payload extraction for generative model watermarks

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new information-theoretic framework for watermarking generative models, enabling more than just machine-made text detection. This framework allows for user attribution, payload extraction, and localization of edited text segments. The study establishes a tight entropy-rate law for multi-user attribution, indicating that attributing text to one of N users requires approximately log(N)/h tokens, where h is the entropy rate. Experiments with GPT-2, Pythia-410M, and Qwen2.5 validated the theoretical predictions. AI

IMPACT Enhances the forensic capabilities of generative models, potentially improving accountability and security in AI-generated content.

RANK_REASON The cluster contains a research paper detailing a new theoretical framework and experimental validation for watermarking generative models.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New framework enables user attribution and payload extraction for generative model watermarks

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Xiaoyu Li, Zheng Gao, Xiaoyan Feng, Jiaojiao Jiang, Yulei Sui, Jiankun Hu ·

    Watermark Forensics for Generative Models: An Information-Theoretic Perspective

    arXiv:2607.13003v1 Announce Type: cross Abstract: A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidden payload, or localize the part that survives edi…

  2. arXiv cs.LG TIER_1 English(EN) · Jiankun Hu ·

    Watermark Forensics for Generative Models: An Information-Theoretic Perspective

    A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidden payload, or localize the part that survives editing. These form a forensic ladder, and we ask wha…

RELATED ENTITIES

RELATED TOPICS