Results 1 to 10 of about 504,243 (126)
Saliency Attack: Towards Imperceptible Black-box Adversarial Attack
ACM Transactions on Intelligent Systems and Technology, 2023 Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency. However, such performance is often accompanied by compromises in attack imperceptibility, hindering the ...
Zeyu Dai, Shengcai Liu, Qing Li
exaly +3 more sources
Generalizable Black-Box Adversarial Attack With Meta Learning
IEEE Transactions on Pattern Analysis and Machine IntelligenceT-PAMI 2022.
Fei Yin, Yong Zhang, Baoyuan Wu
exaly +4 more sources
A black-box adversarial attack for poisoning clustering [PDF]
Pattern Recognition, 2022 Clustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has become imperative.
Cina, AE, Torcinovich, A, Pelillo, M
openaire +4 more sources
Toward Visual Distortion in Black-Box Attacks [PDF]
IEEE Transactions on Image Processing, 2021 Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network.
Nannan Li 0004, Zhenzhong Chen
openaire +3 more sources
Spanning attack: reinforce black-box attacks with unlabeled data [PDF]
Machine Learning, 2020 Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer from the issue of query inefficiency due to the high dimensionality of the input space, and therefore incur a false
Lu Wang 0031 +4 more
openaire +2 more sources
Projection & Probability-Driven Black-Box Attack [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 CVPR2020
Jie Li 0052 +6 more
openaire +2 more sources
Distributed Black-box Attack: Do Not Overestimate Black-box Attacks
, 2022 Accepted by ICLR Workshop ...
Wu, Han +2 more
openaire +2 more sources
Homomorphic Encryption and Some Black Box Attacks [PDF]
, 2020 This paper is a compressed summary of some principal definitions and concepts in the approach to the black box algebra being developed by the authors. We suggest that black box algebra could be useful in cryptanalysis of homomorphic encryption schemes, and that homomorphic encryption is an area of research where cryptography and black box algebra may ...
Alexandre V. Borovik +1 more
openaire +2 more sources
Amora: Black-box Adversarial Morphing Attack [PDF]
Proceedings of the 28th ACM International Conference on Multimedia, 2020 Accepted by ACM MM ...
Run Wang 0001 +6 more
openaire +3 more sources
Stateful Detection of Black-Box Adversarial Attacks [PDF]
Proceedings of the 1st ACM Workshop on Security and Privacy on Artificial Intelligence, 2020 The problem of adversarial examples, evasion attacks on machine learning classifiers, has proven extremely difficult to solve. This is true even when, as is the case in many practical settings, the classifier is hosted as a remote service and so the adversary does not have direct access to the model parameters.
Steven Chen +2 more
openaire +2 more sources