← Search

Won Park

2 accepted papers

2022

Adversarial Unlearning of Backdoors via Implicit Hypergradient

ICLR 2022poster

We propose a minimax formulation for removing backdoors from a given poisoned model based on a small set of clean data. This formulation encompasses much of prior work on backdoor removal. We propose the Implicit Backdoor Adversarial Unlearning (I-BAU) algorithm to solve the minimax. Unlike previous…