转发一篇关于攻击水印的论文
Invisible Image Watermarks Are Provably Removable Using Generative AI
By Xuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna, Yu-Xiang Wang, Lei Li
Abstract: Invisible watermarks safeguard images' copyright by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to remove these invisible watermarks. The proposed attack method first adds random noise to an image to destroy the watermark and then reconstructs the image. This approach is flexible and can be instantiated with many existing image-denoising algorithms and pre-trained generative models such as diffusion models. Through formal proofs and empirical results, we show that all invisible watermarks are vulnerable to the proposed attack. For a particularly resilient watermark, RivaGAN, regeneration attacks remove 93-99% of the invisible watermarks while the baseline attacks remove no more than 3%. However, if we do not require the watermarked image to look the same as the original one, watermarks that keep the image semantically similar can be an alternative defense against our attack. Our finding underscores the need for a shift in research/industry emphasis from invisible watermarks to semantically similar ones. Code is available at https://github.com/XuandongZhao/WatermarkAttacker .
题外话:
1. 国内很多声称嵌入不可见水印的网站实际上使用的只是对比度较低的可见水印，并不能用这种方法移除。
2. 注意不要把 Blindness 和 visibility 混淆，blind watermark指的是不需要原图就能检测的水印。
By Xuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna, Yu-Xiang Wang, Lei Li
https://arxiv.org/abs/2306.01953
Abstract: Invisible watermarks safeguard images' copyright by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to remove these invisible watermarks. The proposed attack method first adds random noise to an image to destroy the watermark and then reconstructs the image. This approach is flexible and can be instantiated with many existing image-denoising algorithms and pre-trained generative models such as diffusion models. Through formal proofs and empirical results, we show that all invisible watermarks are vulnerable to the proposed attack. For a particularly resilient watermark, RivaGAN, regeneration attacks remove 93-99% of the invisible watermarks while the baseline attacks remove no more than 3%. However, if we do not require the watermarked image to look the same as the original one, watermarks that keep the image semantically similar can be an alternative defense against our attack. Our finding underscores the need for a shift in research/industry emphasis from invisible watermarks to semantically similar ones. Code is available at https://github.com/XuandongZhao/WatermarkAttacker .
题外话:
1. 国内很多声称嵌入不可见水印的网站实际上使用的只是对比度较低的可见水印，并不能用这种方法移除。
2. 注意不要把 Blindness 和 visibility 混淆，blind watermark指的是不需要原图就能检测的水印。
