membership-inference-attacks

[NeurIPS D&B '25] The one-stop repository for LLM unlearning

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

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

Loss and Likelihood Based Membership Inference of Diffusion Models

[ICMLW 2026] The official repository for our paper, "Machine Text Detectors are Membership Inference Attacks"

Critical evaluation of CTGAN for tabular data synthesis on UCI Adult Census, with rigorous metrics (Wasserstein, JSD, Frobenius, TSTR) and analysis of structural limitations on zero-inflated variables.

Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions

Privacy-First Recommendation System

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.