A gradient-norm-regularized fine-tuning method, GN-FT, removes backdoor behaviors from audio speech recognition models while keeping clean accuracy high.
Deepface: Closing the gap to human-level performance in face veri- fication,
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.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition
A gradient-norm-regularized fine-tuning method, GN-FT, removes backdoor behaviors from audio speech recognition models while keeping clean accuracy high.