SegPAR, a class-centric decision-based sparse attack with a discrepancy reward, outperforms black-box sparse baselines in semantic segmentation MIoU reduction and sparsity efficiency.
Adversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Adversarial training (AT) is a popular method for training robust deep neural networks (DNNs) against adversarial attacks. Yet, AT suffers from two shortcomings: (i) the robustness of DNNs trained by AT is highly intertwined with the size of the DNNs, posing challenges in achieving robustness in smaller models; and (ii) the adversarial samples employed during the AT process exhibit poor generalization, leaving DNNs vulnerable to unforeseen attack types. To address these dual challenges, this paper introduces adversarial training via adaptive knowledge amalgamation of an ensemble of teachers (AT-AKA). In particular, we generate a diverse set of adversarial samples as the inputs to an ensemble of teachers; and then, we adaptively amalgamate the logtis of these teachers to train a generalized-robust student. Through comprehensive experiments, we illustrate the superior efficacy of AT-AKA over existing AT methods and adversarial robustness distillation techniques against cutting-edge attacks, including AutoAttack.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation
SegPAR, a class-centric decision-based sparse attack with a discrepancy reward, outperforms black-box sparse baselines in semantic segmentation MIoU reduction and sparsity efficiency.