Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking
Department of Industrial and Systems Engineering, University of Minnesota(工业与系统工程系,明尼苏达大学);Google(谷歌);Department of Electrical and Computer Engineering, Princeton University(电气工程与计算机科学系,普林斯顿大学);Stony Brook University(石溪大学)
Liyan Xie, Muhammad Siddeek, Mohamed Seif, Andrea J. Goldsmith, Mengdi Wang
Watermarking has become a key technique for proprietary language models, enabling the distinction between AI-generated and human-written text. However, in many real-world scenarios, LLM-generated content may undergo post-generation edits, such as human revisions or even spoofing attacks, making it critical to detect and localize such modifications. In this work, we introduce a new task: detecting post-generation edits locally made to watermarked LLM outputs. To this end, we propose a combinatorial pattern-based watermarking framework, which partitions the vocabulary into disjoint subsets and embeds the watermark by enforcing a deterministic combinatorial pattern over these subsets during generation. We accompany the combinatorial watermark with a global statistic that can be used to detect the watermark. Furthermore, we design lightweight local statistics to flag and localize potential edits. We introduce two task-specific evaluation metrics, Type-I error rate and detection accuracy, and evaluate our method on open-source LLMs across a variety of editing scenarios, demonstrating strong empirical performance in edit localization.
On the Reliability of Watermarks for Large Language Models
Max-Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Tübingen AI Center(蒂宾根人工智能中心);University of Maryland(马里兰大学);Scuola Normale Superiore di Pisa(比萨高等师范学校);New York University(纽约大学);ELLIS Institute Tübingen(ELLIS蒂宾根研究所)
Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models
College of Computer Science, Chongqing University, China(重庆大学计算机学院);School of Computer Science and Engineering, Nanyang Technological University, Singapore(南洋理工大学计算机科学与工程学院);Institute for Network Sciences and Cyberspace, Tsinghua University, China(清华大学网络科学与网络空间研究院);The Bradley Department of Electronic and Computer Engineering, Virginia Tech(弗吉尼亚理工大学布拉德利电子与计算机工程系)