Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning

Li An, Yujian Liu, Yepeng Liu, Yang Zhang, Yuheng Bu, Shiyu Chang

Keywords: LLM watermarking, Spoofing attack, Piggyback Spoofing attack

TL;DR: The paper proposes a semantic-aware watermarking method that defends against spoofing attacks by using a contrastively trained semantic mapping model to detect semantic distortions.

Abstract: Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria -- high quality of the watermarked text, high detectability, and robustness against removal attack. However, the security against spoofing attacks remains relatively understudied. For example, a piggyback attack can maliciously alter the meaning of watermarked text by transforming it into hate speech, while preserving the original watermark, thereby damaging the reputation of the LLM provider. We identify two core challenges that make defending against spoofing difficult: (1) the need for watermarks to be both sensitive to semantic-distorting changes and insensitive to semantic-preserving edits, and (2) the contradiction between the need to detect global semantic shifts and the local, auto-regressive nature of most watermarking schemes. To address these challenges, we propose a semantic-aware watermarking algorithm that post-hoc embeds watermarks into a given target text while preserving its original meaning. Our method introduces a semantic mapping model, which guides the generation of a green-red token list, contrastively trained to be sensitive to semantic-distorting changes and insensitive to semantic-preserving changes. Experiments on two standard benchmarks demonstrate strong robustness against removal attacks and security against spoofing attacks, including sentiment reversal and toxic content insertion, while maintaining high watermark detectability. Our approach offers a significant step toward more secure and semantically aware watermarking for LLMs.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1214