Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2020 | ICML | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chuan Guo | 1 | 195 | 9.47 |
Tom Goldstein | 2 | 1749 | 91.01 |
Awni Y. Hannun | 3 | 517 | 27.54 |
van der maaten | 4 | 763 | 48.75 |