search

samuel-yeom / ml-privacy-csf18

Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"
MIT License
38 stars 5 forks source link

Colluding Adversary #2

Closed TTitcombe closed 3 years ago

TTitcombe commented 4 years ago

main.py only seems to run linear and tree models, not a CNN with a colluding adversary. Have I interpreted this correctly? Is the code for the colluding adversary available?

samuel-yeom commented 4 years ago

Your interpretation is correct. After digging through some old code, I found this, which was written by my advisor @mfredrik. I haven't tried to run it, but maybe you'll find it helpful.