Proposes a self-aware unlearning method inspired by hypnopaedia that uses model inversion and hypothesis testing to detect and detach backdoor triggers from machine learning models.
Adversarial neuron pruning purifies backdoored deep models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery
Proposes a self-aware unlearning method inspired by hypnopaedia that uses model inversion and hypothesis testing to detect and detach backdoor triggers from machine learning models.