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 variational inference and our formulation. The developed approach combines manifold learning with variational inference to provide adversarial robustness without the need for adversarial training. We show that our approach can provide adversarial robustness even if attackers are aware of the existence of test-time defense. In addition, our approach can also serve as a test-time defense mechanism for variational autoencoders.

翻译：在这项工作中,我们利用多重假设,制定了新的对抗性强力框架。我们的框架为抵御对抗性例子提供了充分的条件。我们开发了一种测试-时间防御方法,配有变式推论和我们的配方。发达的方法结合了多种不同的学习和变式推论,以提供对抗性强力,而不需要对抗性培训。我们表明,即使攻击者知道测试-时间防御的存在,我们的方法也可以提供对抗性强力。此外,我们的方法也可以作为变式自动转换器的测试-时间防御机制。