Abstract
Adversarial attacks represent a threat to every deep neural network. They are particularly effective if they can perturb a given model while remaining undetectable. They have been initially introduced for image classifiers, and are well studied for this task. For time series, few attacks have yet been proposed. Most that have are adaptations of attacks previously proposed for image classifiers. Although these attacks are effective, they generate perturbations containing clearly discernible patterns such as sawtooth and spikes. Adversarial patterns are not perceptible on images, but the attacks proposed to date are readily perceptible in the case of time series. In order to generate stealthier adversarial attacks for time series, we propose a new attack that produces smoother perturbations. We find that smooth perturbations are harder to detect by the naked eye. We also show how adversarial training can improve model robustness against this attack, thus making models less vulnerable.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bhambri, S., Muku, S., Tulasi, A., Buduru, A.B.: A survey of black-box adversarial attacks on computer vision models (2020)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57. IEEE (2017)
Dau, H.A., et al.: The UCR time series archive (2019)
Dong, Y., et al.: Boosting adversarial attacks with momentum. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9185–9193 (2018)
Eykholt, K., et al.: Robust physical-world attacks on deep learning visual classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1625–1634 (2018)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Guillaume, A., Vrain, C., Wael, E.: Time series classification for predictive maintenance on event logs. arXiv preprint arXiv:2011.10996 (2020)
Huan, Z., Wang, Y., Zhang, X., Shang, L., Fu, C., Zhou, J.: Data-free adversarial perturbations for practical black-box attack. In: Lauw, H.W., Wong, R.C.-W., Ntoulas, A., Lim, E.-P., Ng, S.-K., Pan, S.J. (eds.) PAKDD 2020. LNCS (LNAI), vol. 12085, pp. 127–138. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-47436-2_10
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., Muller, P.A.: Adversarial attacks on deep neural networks for time series classification. In: 2019 International Joint Conference on Neural Networks (IJCNN), July 2019
Ismail Fawaz, H.: InceptionTime: finding AlexNet for time series classification. Data Min. Knowl. Disc. 34(6), 1936–1962 (2020)
Jiang, Y., Ma, X., Erfani, S.M., Bailey, J.: Dual head adversarial training (2021)
Kaushik, S., et al.: Ai in healthcare: time-series forecasting using statistical, neural, and ensemble architectures. Front. Big Data 3, 4 (2020)
Kumar, N., Jha, G.K.: A time series ANN approach for weather forecasting. Int. J. Control Theory Comput. Model (IJCTCM) 3(1), 19–25 (2013)
Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: Artificial Intelligence Safety and Security, pp. 99–112. Chapman and Hall/CRC (2018)
Li, J., Schmidt, F., Kolter, Z.: Adversarial camera stickers: a physical camera-based attack on deep learning systems. In: International Conference on Machine Learning, pp. 3896–3904. PMLR (2019)
Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J.: Defense against adversarial attacks using high-level representation guided denoiser. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1778–1787 (2018)
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z.B., Swami, A.: Practical black-box attacks against machine learning (2017)
Rathore, P., Basak, A., Nistala, S.H., Runkana, V.: Untargeted, targeted and universal adversarial attacks and defenses on time series. In: 2020 International Joint Conference on Neural Networks (IJCNN), July 2020
Su, J., Vargas, D.V., Sakurai, K.: One pixel attack for fooling deep neural networks. IEEE Trans. Evol. Comput. 23(5), 828–841 (2019)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Wu, L., Zhu, Z., Tai, C., et al.: Understanding and enhancing the transferability of adversarial examples (2018)
Xie, C., Tan, M., Gong, B., Yuille, A., Le, Q.V.: Smooth adversarial training (2021)
Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A.: Mitigating adversarial effects through randomization. arXiv preprint arXiv:1711.01991 (2017)
Acknowledgement
This work was funded by ArtIC project “Artificial Intelligence for Care” (grant ANR-20-THIA-0006-01) and co-funded by Région Grand Est, Inria Nancy - Grand Est, IHU of Strasbourg, University of Strasbourg and University of Haute-Alsace. The authors would like to thank the providers of the UCR archive as well as the Mésocentre of Strasbourg for providing access to the GPU cluster.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pialla, G. et al. (2022). Smooth Perturbations for Time Series Adversarial Attacks. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)