paper-with-me

홈 › Papers

An Undetectable Watermark for Generative Image Models

2024-10-09 · Sam Gunn, Xuandong Zhao, Dawn Song

We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries. In particular, an undetectable watermark does not degrade image quality under any efficiently computable metric. Our scheme works by selecting the initial latents of a diffusion model using a pseudorandom error-correcting code (Christ and Gunn, 2024), a strategy which guarantees undetectability and robustness. We experimentally demonstrate that our watermarks are quality-preserving and robust using Stable Diffusion 2.1. Our experiments verify that, in contrast to every prior scheme we tested, our watermark does not degrade image quality. Our experiments also demonstrate robustness: existing watermark removal attacks fail to remove our watermark from images without significantly degrading the quality of the images. Finally, we find that we can robustly encode 512 bits in our watermark, and up to 2500 bits when the images are not subjected to watermark removal attacks. Our code is available at https://github.com/XuandongZhao/PRC-Watermark.

📄 PDF Abstract BibTeX arXiv:2410.07369

Code (1)

xuandongzhao/prc-watermark 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Undetectable Watermarks for Language Models

2023-05-25 · Miranda Christ, Sam Gunn, Or Zamir

Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in mode…

Attribute-based Undetectable Watermarking for Generative AI Models

2026-08-04 · Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel, Er-Cheng Tang arxiv

Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs. Existing cryptographic watermarking methods provide …

Deep Learning-based Text-in-Image Watermarking

2024-04-19 · Bishwa Karki, Chun-Hua Tsai, Pei-Chi Huang, Xin Zhong

In this work, we introduce a novel deep learning-based approach to text-in-image watermarking, a method that embeds and extracts textual information within images to enhance data security and integrity. Leveraging the ca…

Deep Learning

Watermarking Should Be Treated as a Monitoring Primitive

2026-05-13 · Toluwani Aremu, Nils Lukas, Jie Zhang arxiv

Watermarking is widely proposed for provenance, attribution, and safety monitoring in generative models, yet is typically evaluated only under adversaries who attempt to evade detection or induce false positives at the l…

LLM Watermarking Using Mixtures and Statistical-to-Computational Gaps

2025-05-02 · Pedro Abdalla, Roman Vershynin

Given a text, can we determine whether it was generated by a large language model (LLM) or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking sch…

Language ModelingLanguage ModellingLarge Language Model