Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
Huajie Chen, Tianqing Zhu, Hailin Yang, Yuchen Zhong, Yang Zhang, Hui Sun, Heng Xu, Zuobin Ying, Lihua Yin, Wanlei Zhou
arXiv:2603.01067v11 citationsh-index: 2
Originality Incremental advance
AI Analysis
This addresses the robustness of watermarking defenses for machine-generated images, which is an incremental contribution to security evaluation.
The paper tackled the problem of removing watermarks from machine-generated images by proposing HIDE&SEEK, a suite of attacks that reliably remove embedded watermarks while preserving high visual fidelity.
Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits of SOTA proactive image watermarking defenses, we propose HIDE&SEEK (HS), a suite of versatile and cost-effective attacks that reliably remove embedded watermarks while preserving high visual fidelity.