Related papers: An Extended Study of Human-like Behavior under Adv…
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…
The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning…
In this paper, we study the adversarial examples existence and adversarial training from the standpoint of convergence and provide evidence that pointwise convergence in ANNs can explain these observations. The main contribution of our…
Generative Adversarial Networks (GANs) have proven to be a powerful framework for learning to draw samples from complex distributions. However, GANs are also notoriously difficult to train, with mode collapse and oscillations a common…
This paper will describe and analyze a new phenomenon that was not known before, which we call "Early Transferability". Its essence is that the adversarial perturbations transfer among different networks even at extremely early stages in…
This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular $\ell_\infty$ and $\ell_2$ bounded adversarial examples). It has been observed that defense mechanisms…
Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it…
Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…
Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. However, a rigorous explanation for why this happens under…
Prior studies have unveiled the vulnerability of the deep neural networks in the context of adversarial machine learning, leading to great recent attention into this area. One interesting question that has yet to be fully explored is the…
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, despite enormous effort, these adversarial examples remained a…
Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. While networks are…
Although adversarial training is known to be effective against adversarial examples, training dynamics are not well understood. In this study, we present the first theoretical analysis of adversarial training in random deep neural networks…
We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted…
Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several application domains. Most research on adversarial examples takes…
In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to…
Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual systems were the only ones capable of this remarkable…
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of adversarial training…
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same…
Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…