STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Liu, Renyang Lam, Kwok-Yan Zhou, Wei Wu, Sixing Zhao, Jun Hu, Dongting Gong, Mingming
Liu, Renyang
Lam, Kwok-Yan
Zhou, Wei
Wu, Sixing
Zhao, Jun
Hu, Dongting
Gong, Mingming
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Extensive studies have revealed that deep neural networks (DNNs) are vulnerable to adversarial attacks, especially black-box ones, which can heavily threaten the DNNs deployed in the real world. Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existing black-box attack methods still suffer from unsatisfactory performance due to the vast number of queries needed to optimize desired perturbations. Besides, the other critical challenge is that adversarial examples built in a noise-adding manner are abnormal and struggle to successfully attack robust models, whose robustness is enhanced by adversarial training against small perturbations. There is no doubt that these two issues mentioned above will significantly increase the risk of exposure and result in a failure to dig deeply into the vulnerability of DNNs. Hence, it is necessary to evaluate DNNs' fragility sufficiently under query-limited settings in a non-additional way. In this paper, we propose the Spatial Transform Black-box Attack (STBA), a novel framework to craft formidable adversarial examples in the query-limited scenario. Specifically, STBA introduces a flow field to the high-frequency part of clean images to generate adversarial examples and adopts the following two processes to enhance their naturalness and significantly improve the query efficiency: a) we apply an estimated flow field to the high-frequency part of clean images to generate adversarial examples instead of introducing external noise to the benign image, and b) we leverage an efficient gradient estimation method based on a batch of samples to optimize such an ideal flow field under query-limited settings. Compared to existing score-based black-box baselines, extensive experiments indicated that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate under query-limited settings.
Citation
R. Liu et al., "STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario," in IEEE Transactions on Multimedia, doi: 10.1109/TMM.2025.3535328
Source
IEEE Transactions on Multimedia
Conference
Keywords
Closed box, Perturbation methods, Robustness, Noise, Transforms, Visualization, Optimization, Computational modeling, Translation, Training
Subjects
Source
Publisher
IEEE