Deep neural networks (DNNs) are powerful nonlinear architectures that are
known to be robust to random perturbations of the input. However, these models
are vulnerable to adversarial perturbations--small input changes crafted
explicitly to fool the model. In this paper, we ask whether a DNN can
distinguish adversarial samples from their normal and noisy counterparts. We
investigate model confidence on adversarial samples by looking at Bayesian
uncertainty estimates, available in dropout neural networks, and by performing
density estimation in the subspace of deep features learned by the model. The
result is a method for implicit adversarial detection that is oblivious to the
attack algorithm. We evaluate this method on a variety of standard datasets
including MNIST and CIFAR-10 and show that it generalizes well across different
architectures and attacks. Our findings report that 85-93% ROC-AUC can be
achieved on a number of standard classification tasks with a negative class
that consists of both normal and noisy samples.

本文介绍了一种利用深度学习神经网络中 Bayesian 不确定性估计和密度估计的方法，可以实现对于对抗样本的检测，具有很好的泛化性能，并在标准分类任务上取得了 85-93% 的 ROC-AUC 表现。