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 …
F Yin, Y Zhang, B Wu, Y Feng, J Zhang… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
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 …
M Li, C Deng, T Li, J Yan, X Gao… - Proceedings of the …, 2020 - openaccess.thecvf.com
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 …
C Ma, L Chen, JH Yong - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
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 …