… the adversarial examples are generated with one of step method. The k adversarial examples
… Possible explanation for this would be that adversarial training tweaks gradient seen from …

… leveraging the regularization power of adversarial examples. … wrt the network parameter for
gradient updates. In other words, … The family of EfficientNets provides a strong baseline, eg., …

… that gradient regularization does not lead to gradient obfuscation or gradient masking. …
or minimized, so that gradient-based attacks fail to produce adversarial examples. For …

… Compared with previous widely used model-dependent methods such as fast gradient
sign (FGS) [9] and the state-ofthe-art method CW [20], which utilize a well-trained classifier to …

… Such modified inputs, also known as adversarial examples (AEs), pose a doubt when
applying deep learning models to security-sensitive applications, such as face recognition, …

… projected gradient ascent based adversarial … norm regularization. This fundamental
connection confirms the long-standing argument that a network’s sensitivity to adversarial examples …

… adversarial training with multi-task cues. In our experiments, we find that the deep gradient
regularization of … While there are a variety of ways to generate adversarial samples, the fastest …

… a new family of adversarial examples for constrastive … attacks with the popular fast gradient
sign method (FGSM) [19]. … Virtual adversarial training: A regularization method for supervised …

… The problem of adversarial examples has shown that modern Neural Network (NN) models
could be rather fragile. Among the more established techniques to solve the problem, one is …

… , we develop a novel family of algorithms that generalize the AT … benign examples when
crafting adversarial examples due to the … Virtual adversarial training: a regularization method for …