Adaptive Test-Time Defense with the Manifold Hypothesis. (arXiv:2210.14404v1 [cs.LG])

In this work, we formulate a novel framework of adversarial robustness using
the manifold hypothesis. Our framework provides sufficient conditions for
defending against adversarial examples. We develop a test-time defense method
with our formulation and variational inference. The developed approach combines
manifold learning with the Bayesian framework to provide adversarial robustness
without the need for adversarial training. We show that our proposed approach
can provide adversarial robustness even if attackers are aware of existence of
test-time defense. In additions, our …

defense manifold test