Popular GitHub Repositories for Membership Inference Attack

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.

A unified, easily extensible repository for LLM unlearning benchmarks (TOFU, MUSE) - enabling new datasets, evaluations, methods, and tasks.

[NeurIPS'24] "Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration"

[AAAI'25 Oral] "MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector".

Privacy Preserving Collaborative Encrypted Network Traffic Classification (Differential Privacy, Federated Learning, Membership Inference Attack, Encrypted Traffic Classification)

[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

[ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs

Collection of tools and resources for managing the statistical disclosure control of trained machine learning models

FederBoost's Federated Gradient Boosting Decision Tree Algorithm, Federated enabled Membership Inference

Membership inference against Federated learning.

The source code for ICML2021 paper When Does Data Augmentation Help With Membership Inference Attacks?

An implementation of loss thresholding attack to infer membership status as described in paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting" (CSF 18) in PyTorch.

Performing membership inference attack (MIA) against Korean language models (LMs).

Implementations on Security and Privacy in ML; Evasion Attack, Model Stealing, Model Poisoning, Membership Inference Attacks, ...

A PyTorch implementation of "HP-MIA: A novel membership inference attack scheme for high membership prediction precision"

DP-UTIL: A Comprehensive Utility Analysis of Differential Privacy in Machine Learning

An implementation of ICLR 22 paper "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" in PyTorch