Concept Removal for Frontier Image Generative Models
Jul. 6, 2026
MGI: Member vs Generated Inference
Jul. 4, 2026
MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning
Jun. 25, 2026
Finding DoRI: Discovery of Retained Images in Diffusion Models
Jun. 24, 2026
Privacy Attacks on Tabular Foundation Models
May. 16, 2026
Benchmarking Empirical Privacy Protection for Adaptations of LLMs
Apr. 28, 2026
Natural Identifiers for Privacy and Data Audits
Apr. 28, 2026
SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
Apr. 25, 2026
Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in AI-Generated Images
Mar. 8, 2026
BitMark: Watermarking Bitwise Autoregressive Image Generative Models
Nov. 30, 2025
Captured by Captions: On Memorization and its Mitigation in Multi-Modal Models
Mar. 3, 2025
Image AutoRegressive Models Leak More Training Data Than Diffusion Models
Feb. 4, 2025
Private Adaptations of Open LLMs Outperform their Closed Alternatives
Dec. 10, 2024
How to prompt LLMs with private data?
Apr. 28, 2024
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
Dec. 10, 2023
On stealing and defending self-supervised models
Feb. 23, 2023
