… Such adversarial examples have been extensively studied in the context of computer vision
… In this work, we show adversarial attacks are also effective when targeting neural network …

… adversarial attacks on deep neural networks achieving k-misclassification for k > 1. We also
provide adversarial attacks … sidered in the context of deep neural networks by Papernot et al. […

… deep neural networks (DNNs) can be easily fooled by adversarial … in attacking and defending
DNNs with adversarial examples … is to review the types of adversarial attacks and defenses, …

… of their robustness to adversarial attacks. Yet, in … of adversarial attacks on attributed graphs,
specifically focusing on models exploiting ideas of graph convolutions. In addition to attacks …

… the network. In fact, some of the latest findings suggest that the existence of adversarial attacks
… To address this problem, we study the adversarial robustness of neural networks through …

… In our analysis to defend neural networks against adversarial attacks, we extend on the
work in [3] which suggests a novel approach for fast generation of adversarial examples. This …

… about their robustness to adversarial attacks. Yet, in … adversarial attacks on attributed graphs,
specifically focusing on models exploiting ideas of graph convolutions. In addition to attacks …

… for more complex over-the-air attacks [15]. The main contributions … adversarial attack in the
modulation recognition scenario; and second, we prove the feasibility of the adversarial attack …

… Attack techniques aim to find adversarial examples that exploit a DNN eg, it classifies the
adversarial … that they can identify or eliminate adversarial attack. These techniques cannot be …

… We compare our model to baselines under three kinds of adversarial attacks: direct targeted
attack (Nettack-Di [8]), influence targeted attack (NettackIn [8]), and non-targeted attack (…