Showing 1–11 of 11 results
/ Date/ Name
Nov 3, 2024Data Extraction Attacks in Retrieval-Augmented Generation via BackdoorsOct 20, 2025Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language ModelsDec 7, 2023Diffence: Fencing Membership Privacy With Diffusion ModelsMay 27, 2024OSLO: One-Shot Label-Only Membership Inference AttacksJan 4, 2022Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial DetectionJan 14, 2026Identifying Models Behind Text-to-Image LeaderboardsOct 7, 2025Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard SecurityJul 19, 2021Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive FeaturesJul 11, 2025Exploiting Leaderboards for Large-Scale Distribution of Malicious ModelsJul 23, 2025Bob's Confetti: Phonetic Memorization Attacks in Music and Video GenerationFeb 1, 2025Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation