Compared to query-based black-box attacks, transfer-based black-box attacks do not
require any information of the attacked models, which ensures their secrecy. However, most …

Object detection has been widely used in many safety-critical tasks, such as autonomous
driving. However, its vulnerability to adversarial examples has not been sufficiently studied …

Recent studies have shown that detectors based on deep models are vulnerable to
adversarial examples, even in the black-box scenario where the attacker cannot access the …

In the scenario of black-box adversarial attack, the target model's parameters are unknown,
and the attacker aims to find a successful adversarial perturbation based on query feedback …

An intriguing property of adversarial examples is their transferability, which suggests that
black-box attacks are feasible in real-world applications. Previous works mostly study the …

Deep models have shown their vulnerability when processing adversarial samples. As for
the black-box attack, without access to the architecture and weights of the attacked model …

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 …

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 …

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

Many adversarial attacks have been proposed to investigate the security issues of deep
neural networks. In the black-box setting, current model stealing attacks train a substitute …