paper-with-me

홈 › Papers

Publicly-Detectable Watermarking for Language Models

2023-10-27 · Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang

We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection sampling and prove that this produces unforgeable and distortion-free (i.e., undetectable without access to the public key) text output. We make use of error-correction to overcome periods of low entropy, a barrier for all prior watermarking schemes. We implement our scheme and find that our formal claims are met in practice.

📄 PDF Abstract BibTeX arXiv:2310.18491

Code (1)

jfairoze/publicly-detectable-watermark 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Watermarking Language Models for Many Adaptive Users

2024-05-17 · Aloni Cohen, Alexander Hoover, Gabe Schoenbach

We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even …

Language Modelling

LLM Watermarking Using Mixtures and Statistical-to-Computational Gaps

2025-05-02 · Pedro Abdalla, Roman Vershynin

Given a text, can we determine whether it was generated by a large language model (LLM) or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking sch…

Language ModelingLanguage ModellingLarge Language Model

On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark

2025-02-07 · Jaiden Fairoze, Guillermo Ortiz-Jimenez, Mel Vecerik, Somesh Jha 외

This work investigates the theoretical boundaries of creating publicly-detectable schemes to enable the provenance of watermarked imagery. Metadata-based approaches like C2PA provide unforgeability and public-detectabili…

Retrieval

Black-Box Detection of Language Model Watermarks

2024-05-28 · Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev

Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which …

Language ModelingLanguage Modellingmodel

Signature vs. Substance: Evaluating the Balance of Adversarial Resistance and Linguistic Quality in Watermarking Large Language Models

2025-08-11 · William Guo, Adaku Uchendu, Ana Smith arxiv

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately de…