|国家预印本平台
首页|Watermark Stealing in Large Language Models

Watermark Stealing in Large Language Models

Watermark Stealing in Large Language Models

来源:Arxiv_logoArxiv
英文摘要

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark stealing (WS) as a fundamental vulnerability of these schemes. We show that querying the API of the watermarked LLM to approximately reverse-engineer a watermark enables practical spoofing attacks, as hypothesized in prior work, but also greatly boosts scrubbing attacks, which was previously unnoticed. We are the first to propose an automated WS algorithm and use it in the first comprehensive study of spoofing and scrubbing in realistic settings. We show that for under $50 an attacker can both spoof and scrub state-of-the-art schemes previously considered safe, with average success rate of over 80%. Our findings challenge common beliefs about LLM watermarking, stressing the need for more robust schemes. We make all our code and additional examples available at https://watermark-stealing.org.

Martin Vechev、Robin Staab、Nikola Jovanovi?

计算技术、计算机技术

Martin Vechev,Robin Staab,Nikola Jovanovi?.Watermark Stealing in Large Language Models[EB/OL].(2024-02-29)[2025-08-02].https://arxiv.org/abs/2402.19361.点此复制

评论