Skip to content

This repository is the official implementation of [Evaluating Membership Inference Through Adversarial Robustness]

Notifications You must be signed in to change notification settings

plll4zzx/Evaluating-Membership-Inference-Through-Adversarial-Robustness

Repository files navigation

Evaluating Membership Inference Through Adversarial Robustness

This repository is the official implementation of [Evaluating Membership Inference Through Adversarial Robustness].

Requirements

To install requirements:

pip install -r requirements.txt

Victim model

To train victim model:

Get_Test_Model.py

📋 you could change dataset and victim model by commenting directly on the code.

Inference strategy I_{dd}

To get directional distance with different T and \lambda:

robust_sphere.py

To evaluate the victim model though I_{dd}:

eval_sphere.py

PGD-AT trained model and membership inference:

To get PGD-AT trained model and evaluate its privacy though difference traditional metric based membership inference methods:

AT_train_test.py

About

This repository is the official implementation of [Evaluating Membership Inference Through Adversarial Robustness]

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages