A two-stage entropy-maximization then entropy-minimization rectification, guided by a low-entropy prior of adversarial examples, improves test-time defense generalization on several benchmarks.
Towards improving robustness of deep neural networks to adversarial perturbations
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
A two-stage entropy-maximization then entropy-minimization rectification, guided by a low-entropy prior of adversarial examples, improves test-time defense generalization on several benchmarks.