… the network. In fact, some of the latest findings suggest that the existence of adversarialattacks … To address this problem, we study the adversarial robustness of neuralnetworks through …
… Such adversarial examples have been extensively studied in the context of computer vision … In this work, we show adversarialattacks are also effective when targeting neuralnetwork …
Z Zheng, P Hong - … neural information processing systems, 2018 - proceedings.neurips.cc
… Various attempts have been conducted to defend adversarialattacks. Papernot et al. [25] … was still highly vulnerable to attacks [3]. Recently, the adversarial training strategy became …
M Ozdag - Procedia Computer Science, 2018 - Elsevier
… deep neuralnetworks (DNNs) can be easily fooled by adversarial … in attacking and defending DNNs with adversarial examples … is to review the types of adversarialattacks and defenses, …
… In our analysis to defend neuralnetworks against adversarialattacks, we extend on the work in [3] which suggests a novel approach for fast generation of adversarial examples. This …
… • Model: We propose a model for adversarialattacks on attributed graphs considering … of attacks where we explicitly distinguish between the attacker and the target nodes. Our attacks …
… about their robustness to adversarialattacks. Yet, in … adversarialattacks on attributed graphs, specifically focusing on models exploiting ideas of graph convolutions. In addition to attacks …
… of adversarialattacks for 19 different neuralnetworks trained to be robust against adversarial attacks on the … of adversarialattacks. We benchmark Jitter against 5 state-of-the-art (SOTA) …
X Zhang, M Zitnik - … neural information processing systems, 2020 - proceedings.neurips.cc
… We compare our model to baselines under three kinds of adversarialattacks: direct targeted attack (Nettack-Di [8]), influence targeted attack (NettackIn [8]), and non-targeted attack (…