<div>
	Analysis of the vulnerability of YOLO neural network models to the Fast Sign Gradient Method attack</div>

Teterev Nikolai V. , Trifonov Vladislav E. , Levina Alla B.

2024 , VOLUME 24, NUMBER 6 ( november-december )

ISSN 2226-1494 (print), ISSN 2500-0373 (online)

Publications

Editor-in-Chief

Nikiforov
Vladimir O.
D.Sc., Prof.

Partners

doi: 10.17586/2226-1494-2024-24-6-1066-1070

Analysis of the vulnerability of YOLO neural network models to the Fast Sign Gradient Method attack

N. V. Teterev, V. E. Trifonov, A. B. Levina

Read the full article

Article in Russian

For citation:

Teterev N.V., Trifonov V.E., Levina A.B. Analysis of the vulnerability of YOLO neural network models to the Fast Sign Gradient Method attack. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2024, vol. 24, no. 6, pp. 1066–1070 (in Russian). doi: 10.17586/2226-1494-2024-24-6-1066-1070

Abstract

The analysis of formalized conditions for creating universal images falsely classified by computer vision algorithms, called adversarial examples, on YOLO neural network models is presented. The pattern of successful creation of a universal destructive image depending on the generated dataset on which neural networks were trained using the Fast Sign Gradient Method attack is identified and studied. The specified pattern is demonstrated for YOLO8, YOLO9, YOLO10, YOLO11 classifier models trained on the standard COCO dataset.

Keywords: adversarial attacks, adversarial example, YOLO, COCO, dataset, neural network

Acknowledgements. The work was performed within the framework of the state assignment of the Ministry of Science and Higher Education of the Russian Federation No. 075-00003-24-01 dated 08.02.2024 (FSEE-2024-0003 project).

References

Chakraborty A., Alam M., Dey V., Chattopadhyay A., Mukhopadhyay D. Adversarial attacks and defences: A survey. arXiv, 2018, arXiv:1810.00069v1. https://doi.org/10.48550/arXiv.1810.00069
Akhtar N., Mian A. Threat of adversarial attacks on deep learning in computer vision: A survey. IEEE Access, 2018, vol. 6, pp. 14410–14430. https://doi.org/10.1109/access.2018.2807385
Goodfellow I., Shlens J., Szegedy C. Explaining and harnessing adversarial examples. Proc. of the 3^rd International Conference on Learning Representations, ICLR 2015, 2015.
Zhang C., Zhang H., Hsieh C.-J. An efficient adversarial attack for tree ensembles. Advances in Neural Information Processing Systems, 2020, vol. 33.
Xiong P., Tegegn M., Sarin J.S., Pal S., Rubin J. It is all about data: A survey on the effects of data on adversarial robustness. ACM Computing Surveys, 2024, vol. 56, no. 7, pp. 1–41. https://doi.org/10.1145/3627817
Zuo C. Regularization effect of fast gradient sign method and its generalization. arXiv, 2018, arXiv:1810.11711. https://doi.org/10.48550/arXiv.1810.11711
Yosinski J., Clune J., Nguyen A., Fuchs T., Lipson H.Understanding neural networks through deep visualization. arXiv, 2015, arXiv:1506.06579v1. https://doi.org/10.48550/arXiv.1506.06579
Carlini N., Wagner D. Towards evaluating the robustness of neural networks. Proc. of the IEEE Symposium on Security and Privacy (SP), 2017, pp. 39–57. https://doi.org/10.1109/sp.2017.49
Li Z., Chen P.-Y., Liu S., Lu S., Xu Y. Zeroth-order optimization for composite problems with functional constraints. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, vol. 36, no. 7, pp. 7453–7461. https://doi.org/10.1609/aaai.v36i7.20709
Guo C., Gardner J., You Y., Wilson A., Weinberger K. Simple black-box adversarial attacks. Proceedings of Machine Learning Research, 2019, vol. 97, pp. 2484–2493.

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License