news

Sep 9, 2025	We introduce a highly efficient yet powerful membership inference attack called Imitative MIA.
Aug 31, 2025	We present a new class of MIA for jointly membership inference, which will be presented at NDSS 2026.
Aug 21, 2025	Our paper on assessment of tabular data synthesis algorithms is accepted by CCS 2025!
May 7, 2025	We present a new privacy threat to online pseudonymity with Language Model Agents.