A compact transformer trained with adversarial attention-map distillation achieves higher accuracy under white-box FGM and PGD attacks than existing adversarial distillation baselines.
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices
A compact transformer trained with adversarial attention-map distillation achieves higher accuracy under white-box FGM and PGD attacks than existing adversarial distillation baselines.