paper-with-me

Papers

Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal

2022-07-17 · Xinwei Liu, Jian Liu, Yang Bai, Jindong Gu, Tao Chen, Xiaojun Jia, Xiaochun Cao

As a common security tool, visible watermarking has been widely applied to protect copyrights of digital images. However, recent works have shown that visible watermarks can be removed by DNNs without damaging their host images. Such watermark-removal techniques pose a great threat to the ownership of images. Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good. From the perspective of the adversary, blind watermark-removal networks can be posed as our target models; then we actually optimize an imperceptible adversarial perturbation on the host images to proactively attack against watermark-removal networks, dubbed Watermark Vaccine. Specifically, two types of vaccines are proposed. Disrupting Watermark Vaccine (DWV) induces to ruin the host image along with watermark after passing through watermark-removal networks. In contrast, Inerasable Watermark Vaccine (IWV) works in another fashion of trying to keep the watermark not removed and still noticeable. Extensive experiments demonstrate the effectiveness of our DWV/IWV in preventing watermark removal, especially on various watermark removal networks.

📄 PDF Abstract BibTeX arXiv:2207.08178

Code (1)

thinwayliu/watermark-vaccine 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios

2025-02-18 · Liangqi Lei, Keke Gai, Jing Yu, Liehuang Zhu 외

Latent diffusion models have exhibited considerable potential in generative tasks. Watermarking is considered to be an alternative to safeguard the copyright of generative models and prevent their misuse. However, in the…

On the Robustness of Watermarking for Autoregressive Image Generation

2026-04-13 · Andreas Müller, Denis Lukovnikov, Shingo Kodama, Minh Pham 외 arxiv

The proliferation of autoregressive (AR) image generators demands reliable detection and attribution of their outputs to mitigate misinformation, and to filter synthetic images from training data to prevent model collaps…

Image Generation

RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees

2024-01-23 · Xun Xian, Ganghua Wang, Xuan Bi, Jayanth Srinivasa 외

Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. This paper introduces a robust and agile plug-and-play watermark detection framework, dubbed as RAW. …

Decoder

Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks

2021-06-18 · Suyoung Lee, Wonho Song, Suman Jana, Meeyoung Cha 외

Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based water…

Signature vs. Substance: Evaluating the Balance of Adversarial Resistance and Linguistic Quality in Watermarking Large Language Models

2025-08-11 · William Guo, Adaku Uchendu, Ana Smith arxiv

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately de…