With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques,
it is critical to ensure the security and robustness of the deployed algorithms. Recently, the …

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial
perturbations to their observations, similar to adversarial examples for classifiers. However …

The adversarial machine learning literature is largely partitioned into evasion attacks on
testing data and poisoning attacks on training data. In this work, we show that adversarial …

Obtaining deep networks that are robust against adversarial examples and generalize well
is an open problem. A recent hypothesis even states that both robust and accurate models …

In this work, we study the implications of the implicit bias of gradient flow on generalization
and adversarial robustness in ReLU networks. We focus on a setting where the data …

The problem of adversarial defenses for image classification, where the goal is to robustify a
classifier against adversarial examples, is considered. Inspired by the hypothesis that these …

Adversarial training (AT) has become the de-facto standard to obtain models robust against
adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on …

Recently, there has been a significant growth of interest in applying software engineering
techniques for the quality assurance of deep learning (DL) systems. One popular direction is …

Electric load forecasting is an essential problem for the power industry, which has a
significant impact on power system operation. Currently, deep learning is proved to be an …

The extreme fragility of deep neural networks, when presented with tiny perturbations in their
inputs, was independently discovered by several research groups in 2013. However …