Adapting program inputs with a layerwise validity score and genetic search improves deep code model accuracy by up to 8.78% without retraining.
On the Effectiveness of Defensive Distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We report experimental results indicating that defensive distillation successfully mitigates adversarial samples crafted using the fast gradient sign method, in addition to those crafted using the Jacobian-based iterative attack on which the defense mechanism was originally evaluated.
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CodeImprove: Program Adaptation for Deep Code Models
Adapting program inputs with a layerwise validity score and genetic search improves deep code model accuracy by up to 8.78% without retraining.