International Conference on Machine Learning (ICML)
Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
International Conference on Machine Learning (ICML)
Finding DoRI: Discovery of Retained Images in Diffusion Models
International Conference on Learning Representations (ICLR)
Natural Identifiers for Privacy and Data Audits in Large Language Models
International Conference on Learning Representations (ICLR)
SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
International Conference on Learning Representations (ICLR)
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models