search

privacytrustlab / ml_privacy_meter

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
MIT License
557 stars 99 forks source link

Code of "MIA via Distillation" #62

Closed jlyang1990 closed 1 year ago

jlyang1990 commented 2 years ago

Hi, I'm reading the paper Enhanced Membership Inference Attacks against Machine Learning Models. It is very well written! I'm wondering if you have plan to open-source the code of "MIA via Distillation", since "MIA via Distillation" is claimed to have better performance than other MIAs already implemented in this package. I'm very interested in the algorithm/implementation details of this attack. Thanks!

changhongyan123 commented 1 year ago

@jlyang1990 , the code is available now. You can find it in the attack_via_reference_or_distill.ipynb.