BURN removes backdoors from trained models by detecting poison samples through adversarial boundary distance and re-labeling them with labels recovered by adversarial perturbations.
Lira: Learnable, imperceptible and robust backdoor attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
BURN: Backdoor Unlearning via Adversarial Boundary Analysis
BURN removes backdoors from trained models by detecting poison samples through adversarial boundary distance and re-labeling them with labels recovered by adversarial perturbations.