Abstract
The existence of adversarial example problem puts forward high demand on the robustness of neural network. This paper proposes a universal adversarial perturbation(UAP) attack method in data-free scenario, which can realize targeted attack to any class specified by the attacker. We design a unique loss function to balance the purpose of perturbing model and targeting label. As far as we know, our method is the first UAP attack method that can achieve targeted attack in data-free scenario. Especially, in federated learning a malicious user can fool other users’ model without being noticed. We hope our attack method can inspire more researchers in the community, and enable them to better understand and defend against UAP attacks.
Supported by organization Nanyang Technological University.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Benz, P., Zhang, C., Imtiaz, T., Kweon, I.S.: Double targeted universal adversarial perturbations. In: Proceedings of the Asian Conference on Computer Vision (2020)
Brown, T.B., Mané, D., Roy, A., Abadi, M., Gilmer, J.: Adversarial patch. arXiv preprint arXiv:1712.09665 (2017)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Finlayson, S.G., Bowers, J.D., Ito, J., Zittrain, J.L., Beam, A.L., Kohane, I.S.: Adversarial attacks on medical machine learning. Science 363(6433), 1287–1289 (2019)
Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27, 2672–2680 (2014)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hirano, H., Takemoto, K.: Simple iterative method for generating targeted universal adversarial perturbations. arXiv preprint arXiv:1911.06502 (2019)
Houben, S., Stallkamp, J., Salmen, J., Schlipsing, M., Igel, C.: Detection of traffic signs in real-world images: the German traffic sign detection benchmark. In: International Joint Conference on Neural Networks, vol. 1288 (2013)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1765–1773 (2017)
Mopuri, K.R., Ganeshan, A., Babu, R.V.: Generalizable data-free objective for crafting universal adversarial perturbations. IEEE Trans. Pattern Anal. Mach. Intell. 41(10), 2452–2465 (2018)
Mopuri, K.R., Garg, U., Babu, R.V.: Fast feature fool: a data independent approach to universal adversarial perturbations. arXiv preprint arXiv:1707.05572 (2017)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026–8037 (2019)
Poursaeed, O., Katsman, I., Gao, B., Belongie, S.: Generative adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4422–4431 (2018)
Reddy Mopuri, K., Krishna Uppala, P., Venkatesh Babu, R.: Ask, acquire, and attack: data-free uap generation using class impressions. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19–34 (2018)
Sam, D.B., Sudharsan, K., Radhakrishnan, V.B., et al.: Crafting data-free universal adversaries with dilate loss (2019)
Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 3–18. IEEE (2017)
Zhang, C., Benz, P., Imtiaz, T., Kweon, I.S.: Understanding adversarial examples from the mutual influence of images and perturbations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14521–14530 (2020)
Acknowledgement
This paper is supported by 1) Singapore Ministry of Education Academic Research Fund Tier 1 RG128/18, Tier 1 RG115/19, Tier 1 RT07/19, Tier 1 RT01/19, Tier 1 RG24/20, and Tier 2 MOE2019-T2-1–176, 2) NTU-WASP Joint Project, 3) Singapore NRF National Satellite of Excellence, Design Science and Technology for Secure Critical Infrastructure NSoE DeST-SCI2019-0012, 4) AI Singapore (AISG) 100 Experiments (100E) programme, and 5) NTU Project for Large Vertical Take-Off & Landing (VTOL) Research Platform.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, X., Bai, T., Zhao, J. (2021). A Data-Free Approach for Targeted Universal Adversarial Perturbation. In: Lu, W., Sun, K., Yung, M., Liu, F. (eds) Science of Cyber Security. SciSec 2021. Lecture Notes in Computer Science(), vol 13005. Springer, Cham. https://doi.org/10.1007/978-3-030-89137-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-89137-4_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89136-7
Online ISBN: 978-3-030-89137-4
eBook Packages: Computer ScienceComputer Science (R0)