论文标题
通过深度度量学习，提高对敏感性和不变性攻击的对抗性鲁棒性
Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning
论文作者
论文摘要
有意制作的对抗样本有效地利用了深层神经网络中的弱点。对抗性鲁棒性的标准方法假定了一个框架来防御通过最小化样品而制作的样品，以使其相应的模型输出变化。这些敏感性攻击利用了模型对任务 - 默认特征的敏感性。可以通过不变性攻击来制定另一种形式的对抗样本，该样本利用了低估相关特征的重要性的模型。先前的文献表明，在严格的L_P有限防御中，防御两种攻击类型方面都有权衡。为了促进对欧几里得距离超越两种类型的攻击的鲁棒性，我们使用指标学习来构架对抗正则化作为最佳运输问题。我们的初步结果表明，在我们的框架中正规化不变的扰动可以改善不变和灵敏度防御。
Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such that its corresponding model output changes. These sensitivity attacks exploit the model's sensitivity toward task-irrelevant features. Another form of adversarial sample can be crafted via invariance attacks, which exploit the model underestimating the importance of relevant features. Previous literature has indicated a tradeoff in defending against both attack types within a strictly L_p bounded defense. To promote robustness toward both types of attacks beyond Euclidean distance metrics, we use metric learning to frame adversarial regularization as an optimal transport problem. Our preliminary results indicate that regularizing over invariant perturbations in our framework improves both invariant and sensitivity defense.
