论文标题
具有歧管假设的对抗性净化
Adversarial Purification with the Manifold Hypothesis
论文作者
论文摘要
在这项工作中，我们使用歧管假设制定了一种新颖的框架，以实现对抗性鲁棒性。该框架提供了足够的条件来防御对抗例子。我们使用此框架开发了一种对抗性纯化方法。我们的方法将多种学习与各种推理结合在一起，以提供对抗性鲁棒性，而无需昂贵的对抗训练。在实验上，即使攻击者意识到防御的存在，我们的方法也可以提供对抗性的鲁棒性。此外，我们的方法还可以作为变异自动编码器的测试时间防御机制。
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.
