Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models

7 November 2023

Papers citing "Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models"

6 / 6 papers shown

Title
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Yixin Cheng Hongcheng Guo Yangming Li Leonid Sigal AAML WaLM 44 0 0 08 May 2025
A Watermark for Black-Box Language Models Dara Bahri John Wieting WaLM 32 1 0 02 Oct 2024
Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods Kathleen C. Fraser Hillary Dawkins S. Kiritchenko DeLMO 30 7 0 21 Jun 2024
Adversarial Diffusion Distillation Axel Sauer Dominik Lorenz A. Blattmann Robin Rombach 130 138 0 28 Nov 2023
Publicly-Detectable Watermarking for Language Models Jaiden Fairoze Sanjam Garg Somesh Jha Saeed Mahloujifar Mohammad Mahmoody Mingyuan Wang WaLM 131 45 0 27 Oct 2023
Supervised GAN Watermarking for Intellectual Property Protection Jianwei Fei Zhihua Xia B. Tondi Mauro Barni WIGM GAN 120 47 0 07 Sep 2022