4 citations · 4 across the 4 of their papers we have counts for
5 papers
You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
Yian Wang, Ali Ebrahimpour-Boroojeny, Hari Sundaram +1
Concept unlearning in text-to-image diffusion models aims to suppress a target concept (e.g., \texttt{horse}) while preserving related but distinct content (e.g., \texttt{donkey}),…
Diffusion Model Attribution via Spectral Coupling of Denoiser Responses
Pragati Shuddhodhan Meshram, Varun Chandrasekaran
Attributing a generated image to its source diffusion model is a fundamental challenge in provenance verification and intellectual property protection. This problem is particularly…
Low-Compute Watermark Removal via Dual-Domain Natural Projection
Pragati Shuddhodhan Meshram, Varun Chandrasekaran
Effective removal of semantic watermarks requires balancing three competing objectives: \emph{high removal success}, \emph{low perceptual distortion}, and \emph{low computational c…
Efficiently Attacking Memorization Scores
Tue Do, Varun Chandrasekaran, Daniel Alabi
Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent app…
Understanding How University Guidelines Address Privacy and Security Issues of Generative AI in Academic Settings
Bei Yi Ng, Jiarui Li, Xinyuan Tong +4
Generative artificial intelligence (GenAI) is transforming the educational landscape by augmenting learning paradigms. However, state-of-the-art GenAI systems driving this transfor…