A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. TPAMI, 2024.

The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning methods. All features: benchmarks, methods, evaluations, models etc. are easily extensible.

Testing membership inference attacks on Deep learning models (LSTM, CNN);

Loss and Likelihood Based Membership Inference of Diffusion Models

apcMIA: Adaptive Perturbation-assisted Contrastive Membership Inference Attack This repository contains the implementation of APCMIA, a black-box membership inference attack framework that combines adaptive perturbation with contrastive learning. It is designed to uncover subtle membership signals in well-generalized.