Timezone: »

 
Generative Autoencoders as Watermark Attackers: Analyses of Vulnerabilities and Threats
Xuandong Zhao · Kexun Zhang · Yu-Xiang Wang · Lei Li

@
in Challenges in Deployable Generative AI »
Event URL: https://openreview.net/forum?id=9xbArVQhnQ »

Invisible watermarks safeguard images' copyrights by embedding hidden messages detectable by owners. It also prevents people from misusing images, especially those generated by AI models. Malicious adversaries can violate these rights by removing the watermarks. In order to remove watermarks without damaging the visual quality, the adversary needs to erase them while retaining the essential information in the image. This is analogous to the encoding and decoding process of generative autoencoders, especially variational autoencoders (VAEs) and diffusion models. We propose a framework using generative autoencoders to remove invisible watermarks and test it using VAEs and diffusions. Our results reveal that, even without specific training, off-the-shelf Stable Diffusion effectively removes most watermarks, surpassing all current attackers. The result underscores the vulnerabilities in existing watermarking schemes and calls for more robust methods for copyright protection.

Keywords: Diffusion Models · secure ai · watermark

Author Information

Xuandong Zhao (UCSB)
Kexun Zhang (University of California, Santa Barbara)
Yu-Xiang Wang (UC Santa Barbara / Amazon)
Lei Li (University of California Santa Barbara)

More from the Same Authors