Adversarial Unlearning of Backdoors via Implicit Hypergradient.

Yi Zeng Si Chen Won Park Z. Morley Mao Ming Jin Ruoxi Jia

Published in: CoRR (2021)

Keyphrases

hidden structure
satisfiability problem
artificial intelligence
trade off
domain knowledge
search engine
computer vision
decision making
face recognition
similarity measure
training data
bayesian networks
preprocessing
relational databases
sat instances