EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Boosting Adversarial Attacks with Nadam Optimizer

Qikun Zhang, Yuzhi Zhang, Yanling Shao, Mengqi Liu, Jianyong Li, Junling Yuan, Ruifang Wang

Electronics · 20.03.2023 · 12 (6) · 1464

DOI: 10.3390/electronics12061464 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 20.03.2023. Verfasst von Qikun Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, key technologies R&D Program of Henan Province, Key scientific research project plans of higher education institutions in Henan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep neural networks are extremely vulnerable to attacks and threats from adversarial examples. These adversarial examples deliberately crafted by attackers can easily fool classification models by adding imperceptibly tiny perturbations on clean images. This brings a great challenge to image security for deep learning. Therefore, studying and designing attack algorithms for generating adversarial examples is essential for building robust models. Moreover, adversarial examples are transferable in that they can mislead multiple different classifiers across models. This makes black-box attacks feasible for practical applications. However, most attack methods have low success rates and weak transferability against black-box models. This is because they often overfit the model during the production of adversarial examples. To address this issue, we propose a Nadam iterative fast gradient method (NAI-FGM), which combines an improved Nadam optimizer with gradient-based iterative attacks. Specifically, we introduce the look-ahead momentum vector and the adaptive learning rate component based on the Momentum Iterative Fast Gradient Sign Method (MI-FGSM). The look-ahead momentum vector is dedicated to making the loss function converge faster and get rid of the poor local maximum. Additionally, the adaptive learning rate component is used to help the adversarial example to converge to a better extreme point by obtaining adaptive update directions according to the current parameters. Furthermore, we also carry out different input transformations to further enhance the attack performance before using NAI-FGM for attack. Finally, we consider attacking the ensemble model. Extensive experiments show that the NAI-FGM has stronger transferability and black-box attack capability than advanced momentum-based iterative attacks. In particular, when using the adversarial examples produced by way of ensemble attack to test the adversarially trained models, the NAI-FGM improves the success rate by 8% to 11% over the other attack methods. Last but not least, the NAI-DI-TI-SI-FGM combined with the input transformation achieves a success rate of 91.3% on average.

Förderung

  • National Natural Science Foundation of China
  • key technologies R&D Program of Henan Province
  • Key scientific research project plans of higher education institutions in Henan Province

Zitieren

APA

Zhang, Q., Zhang, Y., Shao, Y., Liu, M., Li, J., Yuan, J., & Wang, R. (2023). Boosting Adversarial Attacks with Nadam Optimizer. Electronics, 12(6), 1464. https://doi.org/10.3390/electronics12061464

Vancouver

Zhang Q, Zhang Y, Shao Y, Liu M, Li J, Yuan J, et al. Boosting Adversarial Attacks with Nadam Optimizer. Electronics. 2023;12(6):1464. doi:10.3390/electronics12061464

BibTeX
@article{Zhang2023,
  author = {Zhang, Qikun and Zhang, Yuzhi and Shao, Yanling and Liu, Mengqi and Li, Jianyong and Yuan, Junling and Wang, Ruifang},
  title = {Boosting Adversarial Attacks with Nadam Optimizer},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {6},
  pages = {1464},
  doi = {10.3390/electronics12061464}
}
Kostenlos starten →