MIA_Library

This is a library used to collect MIA(membership inference attack) open source project on github. It comes from projects collected by the author, and some projects have been tested.

open project

-Tensorflow privacy

-Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch

-Code for backdoor-assisted membership inference attacks

-Membership Inference Attacks fueled by Few-Shot Learning to deal with Data Integritye Attacks

-Official implementation of "Membership Inference Attacks Against Self-supervised Speech Models"

-Code for CCS 2022 "Membership Inference Attacks by Exploiting Loss Trajectory".

-A library for running membership inference attacks against ML models

-membership-inference-via-backdooring

-Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)

-Full demonstration of the complete attack pipeline (train/attack/evaluate) in 3 domain (table, NLP, Image) (Classification)

-This's code, for "Practical Blind Membership Inference Attack via Differential Comparison" , which is I have learnt yet. We have nine membership inference attack to use.

-Membership Inference Attack on Federated Learning

-Disparate Vulnerability to Membership Inference Attacks

-Code for paper: Understanding Disparate Effects of Membership Inference Attacks and Their Countermeasures

-This is the open source implementation of the calibrated privacy attacks. This code reproduces the results from the paper On the Importance of Difficulty Calibration in Membership Inference Attacks.

-A torch-based implementation of the Membership Inference Attack described in the paper Membership Inference Attacks against Machine Learning Models

-Pytorch implementation of "Membership Inference Attacks are Easier on Difficult Problems", ICCV 2021

-The Audio Auditor: Participant-Level Membership Inference in Internet of Things Voice Services

-Public implementation of ICML'19 paper "White-box vs Black-box: Bayes Optimal Strategies for Membership Inference"

-An implementation of data poisoning attack and membership inference attack in Pytorch

-Implementation for the experiments in the blogpost "Demystifying the Membership Inference Attack" at https://www.mlsecurity.ai/post/demystifying-the-membership-inference-attack

-Membership Inference of Generative Models

-Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation

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

-Code for the paper: Label-Only Membership Inference Attacks

-Citation: Tonni, S. M., Vatsalan, D., Farokhi, F., Kaafar, D., Lu, Z., & Tangari, G. (2020). Data and model dependencies of membership inference attack. arXiv preprint arXiv:2002.06856.