Certified Data Removal from Machine Learning Models

Chuan Guo, Tom Goldstein, Awni Hannun, Laurens van der Maaten,


Thu Jul 16 8 a.m. PDT [ Join Zoom ]
Thu Jul 16 7 p.m. PDT [ Join Zoom ]
Please do not share or post zoom links


Good data stewardship requires removal of data at the request of the data's owner. This raises the question if and how a trained machine-learning model, which implicitly stores information about its training data, should be affected by such a removal request. Is it possible to ``remove'' data from a machine-learning model? We study this problem by defining certified removal: a very strong theoretical guarantee that a model from which data is removed cannot be distinguished from a model that never observed the data to begin with. We develop a certified-removal mechanism for linear classifiers and empirically study learning settings in which this mechanism is practical.

Chat is not available.