no code implementations • 12 May 2024 • Yuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Gong
Our results show that our attack can effectively remove the watermark from a diffusion model such that its generated images are non-watermarked, while maintaining the visual quality of the generated images.
no code implementations • 5 Apr 2024 • Zhengyuan Jiang, Moyang Guo, Yuepeng Hu, Neil Zhenqiang Gong
Several companies--such as Google, Microsoft, and OpenAI--have deployed techniques to watermark AI-generated content to enable proactive detection.
no code implementations • 22 Mar 2024 • Yuepeng Hu, Zhengyuan Jiang, Moyang Guo, Neil Gong
The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature.
1 code implementation • 26 Mar 2023 • Jinyuan Jia, Yupei Liu, Yuepeng Hu, Neil Zhenqiang Gong
PORE can transform any existing recommender system to be provably robust against any untargeted data poisoning attacks, which aim to reduce the overall performance of a recommender system.