Learning a backdoored reference model as a poisonous-sample oracle enables near-perfect training-time backdoor removal with negligible natural-accuracy loss.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
MIND decouples high-dimensional model-induced label noise into subspace components via latent manifold disentanglement and a Latent Decoupling Estimator.
citing papers explorer
-
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
Learning a backdoored reference model as a poisonous-sample oracle enables near-perfect training-time backdoor removal with negligible natural-accuracy loss.
-
MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
MIND decouples high-dimensional model-induced label noise into subspace components via latent manifold disentanglement and a Latent Decoupling Estimator.