3 citations · 4 across the 4 of their papers we have counts for
5 papers
Diffusion Sensitivity Geometry and Strong Duality for Optimal Privacy-Utility Tradeoffs
Tue Do, Daniel Alabi
Existing approaches to differential privacy in diffusion models rely on loose sensitivity bounds and isotropic Gaussian noise, leading to unnecessary estimation error. We develop a…
DIME: Query-Efficient Framework for Membership Inference on Diffusion Models
Tue Do, Daniel Alabi
Membership inference attacks expose whether individual records were used to train a model, yet existing attacks on diffusion models are largely heuristic and can require substantia…
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…
Creator Hearts: Investigating the Impact Positive Signals from YouTube Creators in Shaping Comment Section Behavior
Frederick Choi, Charlotte Lambert, Vinay Koshy +3
Much of the research in online moderation focuses on punitive actions. However, emerging research has shown that positive reinforcement is effective at encouraging desirable behavi…
Facing the Illusion and Reality of Safety in Social VR
Qingxiao Zheng, Tue Ngoc Do, Lingqing Wang +1
The ethical design of social Virtual Reality (VR) is not a new topic, but "safety" concerns of using social VR are escalated to a different level given the heat of the Metaverse. F…