1 citations · 1 across the 12 of their papers we have counts for
5 papers · 1 filter
Diffusion-Based Image Editing for Breaking Robust Watermarks
Yunyi Ni, Finn Carter, Ze Niu +2
Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-…
Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness
Zixuan Fu, Yan Ren, Finn Carter +5
Diffusion models have achieved unprecedented success in image generation but pose increasing risks in terms of privacy, fairness, and security. A growing demand exists to \emph{era…
FADE: Adversarial Concept Erasure in Flow Models
Zixuan Fu, Yan Ren, Finn Carter +5
Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We…
TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models
Finn Carter
Text-to-image diffusion models have shown unprecedented generative capability, but their ability to produce undesirable concepts (e.g.~pornographic content, sensitive identities, c…
ACE: Attentional Concept Erasure in Diffusion Models
Finn Carter
Large text-to-image diffusion models have demonstrated remarkable image synthesis capabilities, but their indiscriminate training on Internet-scale data has led to learned concepts…