arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15364cs.CR
收藏

MarkSweep: 一种通过噪声增强和频率感知去噪的无框移除攻击,针对AI生成图像水印

MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoising

Department of Electrical;Computer Engineering, Queen’s University, Kingston, Canada

Jie Cao, Zelin Zhang, Qi Li, Jianbing Ni

AI总结:

MarkSweep通过噪声增强和频率感知去噪技术,有效移除AI生成图像中的水印,降低水印方案的比特精度至67%以下,同时保持图像质量。

摘要:

AI水印将不可见信号嵌入图像中,以提供溯源信息并识别内容为AI生成。在本文中,我们介绍了MarkSweep,一种新颖的水印移除攻击,能够有效擦除嵌入的水印,而不会降低视觉质量。MarkSweep首先通过边缘感知的高斯扰动在高频区域放大水印噪声,并将其注入干净图像中以训练去噪网络。该网络随后整合两个模块,可学习的频率分解模块和频率感知融合模块,以抑制放大噪声并消除水印痕迹。理论分析和广泛的实验表明,不可见水印对MarkSweep高度易感,该攻击能有效移除嵌入的水印,使HiDDeN和Stable Signature水印方案的比特精度降至67%以下,同时保持AI生成图像的感知质量。

英文摘要:

AI watermarking embeds invisible signals within images to provide provenance information and identify content as AI-generated. In this paper, we introduce MarkSweep, a novel watermark removal attack that effectively erases the embedded watermarks from AI-generated images without degrading visual quality. MarkSweep first amplifies watermark noise in high-frequency regions via edge-aware Gaussian perturbations and injects it into clean images for training a denoising network. This network then integrates two modules, the learnable frequency decomposition module and the frequency-aware fusion module, to suppress amplified noise and eliminate watermark traces. Theoretical analysis and extensive experiments demonstrate that invisible watermarks are highly vulnerable to MarkSweep, which effectively removes embedded watermarks, reducing the bit accuracy of HiDDeN and Stable Signature watermarking schemes to below 67%, while preserving perceptual quality of AI-generated images.

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。

↑