Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
This work provides a more reliable benchmark for evaluating emerging adversarial defenses, which is crucial for researchers in adversarial machine learning, though it is incremental as it focuses on improving assessment methods.
The paper tackled the problem of overestimated robustness in Dummy Classes-based defenses by revealing that conventional attacks fail because they align with the defense mechanism, and proposed DAWA to address this gap, reducing measured robustness from 58.61% to 29.52% on CIFAR-10.
Adversarial robustness evaluation faces a critical challenge as new defense paradigms emerge that can exploit limitations in existing assessment methods. This paper reveals that Dummy Classes-based defenses, which introduce an additional "dummy" class as a safety sink for adversarial examples, achieve significantly overestimated robustness under conventional evaluation strategies like AutoAttack. The fundamental limitation stems from these attacks' singular focus on misleading the true class label, which aligns perfectly with the defense mechanism--successful attacks are simply captured by the dummy class. To address this gap, we propose Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that simultaneously targets both the true label and dummy label with adaptive weighting during adversarial example synthesis. Extensive experiments demonstrate that DAWA effectively breaks this defense paradigm, reducing the measured robustness of a leading Dummy Classes-based defense from 58.61% to 29.52% on CIFAR-10 under l_infty perturbation (epsilon=8/255). Our work provides a more reliable benchmark for evaluating this emerging class of defenses and highlights the need for continuous evolution of robustness assessment methodologies.