NT-ML combines non-target label training and mutual learning to purify a backdoored model using a small set of clean samples.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning
NT-ML combines non-target label training and mutual learning to purify a backdoored model using a small set of clean samples.