On the Learnability of Watermarks for Language Models

On the Learnability of Watermarks for Language Models

7 December 2023

Tatsunori Hashimoto

Papers citing "On the Learnability of Watermarks for Language Models"

11 / 11 papers shown

Title
Edit Distance Robust Watermarks for Language Models Noah Golowich Ankur Moitra AAML WaLM 29 5 0 04 Jun 2024
Black-Box Detection of Language Model Watermarks Thibaud Gloaguen Nikola Jovanović Robin Staab Martin Vechev 35 5 0 28 May 2024
WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off Eva Giboulot Furon Teddy WaLM 29 12 0 06 Mar 2024
Watermarking Makes Language Models Radioactive Tom Sander Pierre Fernandez Alain Durmus Matthijs Douze Teddy Furon WaLM 29 11 0 22 Feb 2024
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs Xuandong Zhao Lei Li Yu-Xiang Wang 47 12 0 08 Feb 2024
Optimizing watermarks for large language models Bram Wouters WaLM 24 2 0 28 Dec 2023
Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models Hanlin Zhang Benjamin L. Edelman Danilo Francati Daniele Venturi G. Ateniese Boaz Barak WaLM 138 53 0 07 Nov 2023
Publicly-Detectable Watermarking for Language Models Jaiden Fairoze Sanjam Garg Somesh Jha Saeed Mahloujifar Mohammad Mahmoody Mingyuan Wang WaLM 139 45 0 27 Oct 2023
Distillation-Resistant Watermarking for Model Protection in NLP Xuandong Zhao Lei Li Yu-Xiang Wang WaLM 81 17 0 07 Oct 2022
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks Xuanli He Qiongkai Xu Yi Zeng Lingjuan Lyu Fangzhao Wu Jiwei Li R. Jia WaLM 168 71 0 19 Sep 2022
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark Xuanli He Qiongkai Xu Lingjuan Lyu Fangzhao Wu Chenguang Wang WaLM 160 92 0 05 Dec 2021