Evolutionary Art Attack for Black-Box Adversarial Example Generation
IEEE Transactions on Evolutionary Computation · 2025-08 · 29 (4) · 1343-1355
DOI: 10.1109/tevc.2024.3391063 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Evolutionary Computation, 2025-08. Verfasst von Phoenix Neale Williams und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: UKRI Future Leaders Fellowship, National Natural Science Foundation of China, Royal Society.
Abstract (Originalsprache)
Deep neural networks (DNNs) have achieved remarkable performance in various tasks, including image classification. However, recent research has revealed the susceptibility of trained DNNs to subtle perturbations introduced into input images. Addressing these vulnerabilities is pivotal, leading to a significant area of study focused on developing attack algorithms capable of generating potent adversarial images. In scenarios where access to gradient information is restricted (black-box scenario), many existing methods introduce optimized perturbations to each individual pixels of an image to cause trained DNNs to misclassify. However, due to the high-dimensional nature of this approach, current methods have inherent limitations. In contrast, our proposed approach involves the construction of perturbations by concatenating a series of overlapping semi-transparent shapes. Through the optimization of these shapes’ characteristics, we generate perturbations that result in the desired misclassification by the DNN. By conducting a series of attacks on state-of-the-art DNNs trained of CIFAR-10 and Imagenet datasets, our method consistently outperforms existing attack algorithms in terms of both query efficiency and success rate.
Förderung
- UKRI Future Leaders Fellowship
- National Natural Science Foundation of China
- Royal Society
- Engineering and Physical Sciences Research Council
- Kan Tong Po Fellowship
- Amazon Research Award and Alan Turing Fellowship
Zitieren
APA
Williams, P. N., Li, K., & Min, G. (2025). Evolutionary Art Attack for Black-Box Adversarial Example Generation. IEEE Transactions on Evolutionary Computation, 29(4), 1343-1355. https://doi.org/10.1109/tevc.2024.3391063
Vancouver
Williams PN, Li K, Min G. Evolutionary Art Attack for Black-Box Adversarial Example Generation. IEEE Transactions on Evolutionary Computation. 2025;29(4):1343-1355. doi:10.1109/tevc.2024.3391063
BibTeX
@article{Williams2025,
author = {Williams, Phoenix Neale and Li, Ke and Min, Geyong},
title = {Evolutionary Art Attack for Black-Box Adversarial Example Generation},
journal = {IEEE Transactions on Evolutionary Computation},
year = {2025},
volume = {29},
number = {4},
pages = {1343--1355},
doi = {10.1109/tevc.2024.3391063}
}
EUVIMED