Abstract Machine learning (ML), especially deep neural networks (DNNs) have been widely
used in various applications, including several safety-critical ones (eg autonomous driving) …

Adversarial attacks have been extensively studied in recent years since they can identify the
vulnerability of deep learning models before deployed. In this paper, we consider the black …

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on
transferability, where an adversarial instance generated for a locally trained model can" …

Existing black-box attacks on deep neural networks (DNNs) have largely focused on
transferability, where an adversarial instance generated for a locally trained model can …

This work studies black-box adversarial attacks against deep neural networks (DNNs),
where the attacker can only access the query feedback returned by the attacked DNN …

Decision-based black-box adversarial attacks (decision-based attack) pose a severe threat
to current deep neural networks, as they only need the predicted label of the target model to …

Deep neural networks (DNNs) have demonstrated excellent performance on various tasks,
however they are under the risk of adversarial examples that can be easily generated when …

Abstract We propose the Square Attack, a score-based black-box l_2 l 2-and l_ ∞ l∞-
adversarial attack that does not rely on local gradient information and thus is not affected by …

It is a challenging task to fool an image classifier based on deep neural networks under the
black-box setting where the target model can only be queried. Among existing black-box …

Classic black-box adversarial attacks can take advantage of transferable adversarial
examples generated by a similar substitute model to successfully fool the target model …