arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01067cs.CRcs.AI

Hide&Seek: 通过像素级重建以极低成本去除图像水印

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

AI总结:

HIDE&SEEK通过像素级重建以极低成本高效去除图像水印,提升图像安全性。

摘要:

水印技术已发展为对抗机器生成图像(MGIs)滥用的关键防御手段。然而,这些保护措施的鲁棒性仍缺乏深入研究。为揭示现有前沿图像水印防御措施的局限性,我们提出HIDE&SEEK(HS),一套多功能且成本效益高的攻击方法,能够可靠地去除嵌入水印同时保持高质量的视觉保真度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑