Certified Data Removal from Machine Learning Models

ICML 2020

Certified Data Removal from Machine Learning Models

Jul 12, 2020
|
53 views
|
Details
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. Speakers: Chuan Guo, Tom Goldstein, Awni Hannun, Laurens Van Der Maaten

Comments
loading...