Characterising Machine Unlearning through Definitions and Implementations - Dr Nicolas Papernot (University of Toronto)

The OATML group is pleased to host Professor Nicolas Papernot of the University of Toronto.

The need for machine unlearning, i.e., obtaining a model one would get without training on a subset of data, arises from privacy legislation and as a potential solution to data poisoning or copyright claims. This talk will cover approaches that provide exact unlearning: these approaches output the same distribution of models as would have been obtained by training without the subset of data to be unlearned in the first place. While such approaches can be computationally expensive, we discuss why it is difficult to relax the guarantee they provide to pave the way for more efficient approaches. The talk will also explore whether we can verify unlearning. Here we show how an entity can claim plausible deniability when challenged about an unlearning request that was claimed to be processed, and conclude that at the level of model weights, being unlearnt is not always a well-defined property. Instead, unlearning is an algorithmic property.

Nicolas is an Assistant Professor at the University of Toronto, in the Department of Electrical and Computer Engineering and the Department of Computer Science. He is also a faculty member at the Vector Institute where he holds a Canada CIFAR AI Chair, and a faculty affiliate at the Schwartz Reisman Institute. He was named an Alfred P. Sloan Research Fellow in Computer Science in 2022 and a Member of the Royal Society of Canada College in 2023.