search

privacytrustlab / ml_privacy_meter

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
MIT License
588 stars 100 forks source link

can i attack linear regression、logistic、XGBoost models? #47

Closed yangshaojie0123 closed 1 year ago

yangshaojie0123 commented 3 years ago

1)how can i attack these models? 2)can i attack some models like scikit-learn.job joblib?

amad-person commented 3 years ago

Hi @yangshaojie0123, you can attack linear/logistic regression models by using a single layer Sequential model (example on tensorflow docs). You'll need to pass tensorflow models to the tool if I'm not wrong. I am not sure if XGBoost can be used. Perhaps you can try using boosted trees in tensorflow (docs link).