Attacking LLM Watermarks by Exploiting Their Strengths

arXiv:2402.16187v1 Announce Type: new
Abstract: Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that aims to embed information in the output of a model to verify its source, is useful for mitigating misuse of such AI-generated content. However, existing watermarking schemes remain surprisingly susceptible to attack. In particular, we show that desirable properties shared by existing LLM watermarking systems such as quality preservation, robustness, …

applications arxiv code cs.cl cs.cr cs.lg exploiting generated generative generative models human images information llm mirror text verify watermarking watermarks