FTM combines optimized, attack-specific feature perturbations with clean feature mixup and a momentum-based stochastic update, improving targeted attack transferability over prior single-run baselines.
Introducing competition to boost the transferability of targeted adversarial examples through clean feature mixup
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Transferable Targeted Attacks with Feature Tuning Mixup
FTM combines optimized, attack-specific feature perturbations with clean feature mixup and a momentum-based stochastic update, improving targeted attack transferability over prior single-run baselines.