Factory > Showcase > DisparateVulnerability
Name:
DisparateVulnerability
Description:
Disparate Vulnerability to Membership Inference Attacks
Professor — Lab:
Carmela Troncoso — Security and Privacy Engineering Laboratory
Technical description:
A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. DisparateVulnerability helps in measuring how much a given model can be inverted.
Papers:
Project status:
inactive — entered showcase: 2022-07-07 — entry updated: 2022-08-11
Source code:
Lab GitHub - last commit: 2021-10-20
Code quality:
Prototype
Project type:
Simulation, Experiments
Programming language:
Python
License:
MIT