A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a watermark is embedded into an AI-generated content before it is released. A content is detected as AI-generated if a similar watermark can be decoded from it. In this work, we perform a systematic study on the robustness of such watermark-based AI-generated content detection. We focus on AI-generated images. Our work shows that an attacker can post-process a watermarked image via adding a small, human-imperceptible perturbation to it, such that the post-processed image evades detection while maintaining its visual quality. We show the effectiveness of our attack both theoretically and empirically. Moreover, to evade detection, our adversarial post-processing method adds much smaller perturbations to AI-generated images and thus better maintain their visual quality than existing popular post-processing methods such as JPEG compression, Gaussian blur, and Brightness/Contrast. Our work shows the insufficiency of existing watermark-based detection of AI-generated content, highlighting the urgent needs of new methods. Our code is publicly available: https://github.com/zhengyuan-jiang/WEvade.
Towards Robust Content Watermarking Against Removal and Forgery Attacks
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学);University of Waterloo(滑铁卢大学)
本文提出Instance-Specific watermarking with Two-Sided detection方法,通过动态控制水印注入时间和模式提升鲁棒性,有效对抗移除和伪造攻击。
University of California, Berkeley(加州大学伯克利分校);Columbia University(哥伦比亚大学);Cornell University(康奈尔大学);Anthropic;Oregon State University(俄勒冈州立大学);Google DeepMind(谷歌DeepMind);ETH Zurich(苏黎世联邦理工学院);University of Wisconsin–Madison(威斯康星大学麦迪逊分校);Carnegie Mellon University(卡内基梅隆大学);University of California, San Diego(加州大学圣地亚哥分校)
How does Watermarking Affect Visual Language Models in Document Understanding?
Southeast University, China(东南大学);University of California, Merced, USA(加州大学默塞德分校);National University of Singapore, Singapore(新加坡国立大学);The University of Queensland, Australia(昆士兰大学)
FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
University of California, Santa Cruz(加州大学圣克鲁兹分校);The University of Hong Kong(香港大学);University of Science and Technology of China(中国科学技术大学);IEG, Tencent(腾讯IEG);Fudan University(复旦大学)
Unforgeable Watermarks for Language Models via Robust Signatures
Paul G. Allen School of Computer Science & Engineering, University of Washington(保罗·G·艾伦计算机科学与工程学院,华盛顿大学);Data Science Institute, University of Chicago(数据科学研究所,芝加哥大学)
Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China(西安交通大学计算机科学与工程学院);State Grid Henan Marketing Service Center, Henan, China(国网河南营销服务中心);Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China(中国科学院大学网络安全学院);School of Information Technology, Deakin University, Geelong, Australia(迪金大学信息技术学院)
A General Approach for Using Deep Neural Network for Digital Watermarking
School of Computer Science and Technology, Nantong University(南通大学计算机科学与技术学院);School of Technology, Environments and Design, University of Tasmania(塔斯马尼亚大学技术、环境与设计学院)