Abstract
We aim at demonstrating the influence of diversity in the ensemble of CNNs on the detection of black-box adversarial instances and hardening the generation of white-box adversarial attacks. To this end, we propose an ensemble of diverse specialized CNNs along with a simple voting mechanism. The diversity in this ensemble creates a gap between the predictive confidences of adversaries and those of clean samples, making adversaries detectable. We then analyze how diversity in such an ensemble of specialists may mitigate the risk of the black-box and white-box adversarial examples. Using MNIST and CIFAR-10, we empirically verify the ability of our ensemble to detect a large portion of well-known black-box adversarial examples, which leads to a significant reduction in the risk rate of adversaries, at the expense of a small increase in the risk rate of clean samples. Moreover, we show that the success rate of generating white-box attacks by our ensemble is remarkably decreased compared to a vanilla CNN and an ensemble of vanilla CNNs, highlighting the beneficial role of diversity in the ensemble for developing more robust models.
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
Notes
- 1.
For convenience, \(\mathcal {W}\) is dropped from \(h_\mathcal {W}(\cdot )\).
References
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, JMLR. org (2017), pp. 1321–1330 (2017)
Eykholt, K., et al.: Robust physical-world attacks on deep learning models. arXiv preprint arXiv:1707.08945 (2017)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
Metzen, J.H., Genewein, T., Fischer, V., Bischoff, B.: On detecting adversarial perturbations. In: Proceedings of the 5th International Conference on Learning Representations (ICLR) (2017)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Liao, F., Liang, M., Dong, Y., Pang, T., Zhu, J., Hu, X.: Defense against adversarial attacks using high-level representation guided denoiser. arXiv preprint arXiv:1712.02976 (2017)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Feinman, R., Curtin, R.R., Shintre, S., Gardner, A.B.: Detecting adversarial samples from artifacts. arXiv preprint arXiv:1703.00410 (2017)
Grosse, K., Manoharan, P., Papernot, N., Backes, M., McDaniel, P.: On the (statistical) detection of adversarial examples. arXiv preprint arXiv:1702.06280 (2017)
Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: Advances in Neural Information Processing Systems, pp. 7167–7177 (2018)
Zhang, H., Chen, H., Song, Z., Boning, D., Dhillon, I.S., Hsieh, C.J.: The limitations of adversarial training and the blind-spot attack. arXiv preprint arXiv:1901.04684 (2019)
Tramèr, F., Boneh, D.: Adversarial training and robustness for multiple perturbations. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2019)
Liu, Y., Chen, X., Liu, C., Song, D.: Delving into transferable adversarial examples and black-box attacks. arXiv preprint arXiv:1611.02770 (2016)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Charles, Z., Rosenberg, H., Papailiopoulos, D.: A geometric perspective on the transferability of adversarial directions. arXiv preprint arXiv:1811.03531 (2018)
Bendale, A., Boult, T.E.: Towards open set deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1563–1572 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
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)
He, W., Wei, J., Chen, X., Carlini, N., Song, D.: Adversarial example defenses: ensembles of weak defenses are not strong. arXiv preprint arXiv:1706.04701 (2017)
Huang, R., Xu, B., Schuurmans, D., Szepesvári, C.: Learning with a strong adversary. arXiv preprint arXiv:1511.03034 (2015)
Tramèr, F., Kurakin, A., Papernot, N., Boneh, D., McDaniel, P.: Ensemble adversarial training: attacks and defenses. arXiv preprint arXiv:1705.07204 (2017)
Rozsa, A., Rudd, E.M., Boult, T.E.: Adversarial diversity and hard positive generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 25–32 (2016)
Lu, J., Issaranon, T., Forsyth, D.: Safetynet: detecting and rejecting adversarial examples robustly. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
Meng, D., Chen, H.: Magnet: a two-pronged defense against adversarial examples (2017)
Strauss, T., Hanselmann, M., Junginger, A., Ulmer, H.: Ensemble methods as a defense to adversarial perturbations against deep neural networks. arXiv preprint arXiv:1709.03423 (2017)
Kariyappa, S., Qureshi, M.K.: Improving adversarial robustness of ensembles with diversity training. arXiv preprint arXiv:1901.09981 (2019)
Acknowledgements
This work was funded by NSERC-Canada, Mitacs, and Prompt-Québec. We thank Annette Schwerdtfeger for proofreading the paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Abbasi, M., Rajabi, A., Gagné, C., Bobba, R.B. (2020). Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks. In: Goutte, C., Zhu, X. (eds) Advances in Artificial Intelligence. Canadian AI 2020. Lecture Notes in Computer Science(), vol 12109. Springer, Cham. https://doi.org/10.1007/978-3-030-47358-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-47358-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-47357-0
Online ISBN: 978-3-030-47358-7
eBook Packages: Computer ScienceComputer Science (R0)