Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

Adaptive defenses, which optimize at test time, promise to improve adversarial robustness.
We categorize such adaptive test-time defenses, explain their potential benefits and …

Deep neural networks have achieved remarkable success in machine learning, computer
vision, and pattern recognition in the last few decades. Recent studies, however, show that …

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning,
presenting a well-structured review of up-to-date techniques to assess the vulnerability of …

Whilst adversarial training has been proven to be one most effective defending method
against adversarial attacks for deep neural networks, it suffers from over-fitting on training …

The phenomenon of adversarial examples illustrates one of the most basic vulnerabilities of
deep neural networks. Among the variety of techniques introduced to surmount this inherent …

In response to the threat of adversarial examples, adversarial training provides an attractive
option for improving robustness by training models on online-augmented adversarial …

A trustworthy AI model should be robust to perturbed data, where robustness correlates with
the dimensionality and linearity of feature representations in the model latent space. Existing …

Abstract Generative Adversarial Networks (GANs) are one of the most popular and powerful
models to learn the complex high dimensional distributions. However, they usually suffer …

The decisions of state-of-the-art image classifiers based on neural networks can be easily
changed by small perturbations of the input which, at the same time, would not fool humans …