Abstract
Adversarial example attacks twist an image to cause image classifiers to output a wrong prediction, yet the perturbation is too subtle to be perceived by a human. Existing research has focused on improving the accuracy of image classifiers as a defense. In this paper, we consider the problem of thwarting adversarial example attacks from a different aspect. Instead of developing better image classifiers, our idea is to make images themselves more resilient to the attacks. Specifically, we propose to convert an image into an adversary-proof example to have three properties: 1) The modification is barely noticeable to human eyes; 2) The new image will receive same predictions from image classifiers; and 3) It is much harder for one to compute an adversarial example from the new image than from the original one. We present two solutions to compute adversary-proof examples, and evaluate their performance with two datasets, MNIST and CIFAR10. Our results show that the concept of adversary-proof example can indeed serve effectively as the first line of defense against adversarial example attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baluja, S., Fischer, I.: Adversarial transformation networks: learning to generate adversarial examples. arXiv preprint arXiv:1703.09387 (2017)
Carlini, N., Wagner, D.: Adversarial examples are not easily detected: bypassing ten detection methods. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 3–14. ACM (2017)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: IEEE Symposium on Security and Privacy, pp. 39–57. IEEE (2017)
Cohen, J.M., Rosenfeld, E., Kolter, J.Z.: Certified adversarial robustness via randomized smoothing. arXiv preprint arXiv:1902.02918 (2019)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (ICLR) (2015)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)
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)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: International Conference on Learning Representations (2018)
Meng, D., Chen, H.: MagNet: a two-pronged defense against adversarial examples. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 135–147. ACM (2017)
Nayebi, A., Ganguli, S.: Biologically inspired protection of deep networks from adversarial attacks. arXiv preprint arXiv:1703.09202 (2017)
Papernot, N., McDaniel, P., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE Symposium on Security and Privacy (SP), pp. 582–597. IEEE (2016)
Phan, N., Jin, R., Thai, M.T., Hu, H., Dou, D.: Preserving differential privacy in adversarial learning with provable robustness. arXiv preprint arXiv:1903.09822 (2019)
Qiu, H., Xiao, C., Yang, L., Yan, X., Lee, H., Li, B.: SemanticAdv: generating adversarial examples via attribute-conditioned image editing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 19–37. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_2
Raghunathan, A., Steinhardt, J., Liang, P.: Certified defenses against adversarial examples. arXiv preprint arXiv:1801.09344 (2018)
Szegedy, C., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (2014)
Tramer, F., Carlini, N., Brendel, W., Madry, A.: On adaptive attacks to adversarial example defenses. arXiv preprint arXiv:2002.08347 (2020)
Tramèr, F., Kurakin, A., Papernot, N., Boneh, D., McDaniel, P.: Ensemble adversarial training: attacks and defenses. arXiv preprint arXiv:1705.07204 (2017)
Wong, E., Rice, L., Kolter, J.Z.: Fast is better than free: revisiting adversarial training. arXiv preprint arXiv:2001.03994 (2020)
Zhang, S., Gao, H., Rao, Q.: Defense against adversarial attacks by reconstructing images. IEEE Trans. Image Process. 30, 6117–6129 (2021)
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
Tian, S., Cai, Y., Bao, F., Oruganti, R. (2022). Making Images Resilient to Adversarial Example Attacks. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13531. Springer, Cham. https://doi.org/10.1007/978-3-031-15934-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-15934-3_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15933-6
Online ISBN: 978-3-031-15934-3
eBook Packages: Computer ScienceComputer Science (R0)