SHIELD uses a hypernetwork with IBP training and a new Interval MixUp technique to achieve certified robustness in continual learning, reporting state-of-the-art adversarial accuracy on MNIST, CIFAR-100, and miniImageNet splits.
Adversarial Purification with the Manifold Hypothesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this work, we formulate a novel framework for adversarial robustness using the manifold hypothesis. This framework provides sufficient conditions for defending against adversarial examples. We develop an adversarial purification method with this framework. Our method combines manifold learning with variational inference to provide adversarial robustness without the need for expensive adversarial training. Experimentally, our approach can provide adversarial robustness even if attackers are aware of the existence of the defense. In addition, our method can also serve as a test-time defense mechanism for variational autoencoders.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
SHIELD uses a hypernetwork with IBP training and a new Interval MixUp technique to achieve certified robustness in continual learning, reporting state-of-the-art adversarial accuracy on MNIST, CIFAR-100, and miniImageNet splits.