Abstract
Deep neural networks (DNNs) have made great progress in recent years. Unfortunately, DNNs are found to be vulnerable to adversarial examples that are injected with elaborately crafted perturbations. In this paper, we propose a defense method named DeT, which can (1) defend against adversarial examples generated by common attacks, and (2) correctly label adversarial examples with both small and large perturbations. DeT is a transferability-based defense method, which to the best of our knowledge is the first such attempt. Our experimental results demonstrate that DeT can work well under both black and gray box attacks. We hope that DeT will be a benchmark in the research community for measuring DNN attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The details of reformers will be explained in Sect. 3.
- 2.
References
Cao, X., Gong, N.Z.: Mitigating evasion attacks to deep neural networks via region-based classification. In: Proceedings of the 33rd Annual Computer Security Applications Conference, pp. 278–287. ACM (2017)
Carlini, N., Wagner, D.: MagNet and efficient defenses against adversarial attacks are not robust to adversarial examples. arXiv preprint arXiv:1711.08478 (2017)
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)
Du, T., Ji, S., Li, J., Gu, Q., Wang, T., Beyah, R.: SirenAttack: generating adversarial audio for end-to-end acoustic systems. arXiv preprint arXiv:1901.07846 (2019)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. Computer Science (2014)
Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645–6649. IEEE (2013)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)
Javaid, A., Niyaz, Q., Sun, W., Alam, M.: A deep learning approach for network intrusion detection system. In: Proceedings of the 9th EAI International Conference on Bio-inspired Information and Communications Technologies (formerly BIONETICS), pp. 21–26. ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering) (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Li, J., Ji, S., Du, T., Li, B., Wang, T.: TextBugger: generating adversarial text against real-world applications. In: NDSS (2019)
Li, X., et al.: Adversarial examples versus cloud-based detectors: a black-box empirical study. arXiv preprint arXiv:1901.01223 (2019)
Ling, X., et al.: DEEPSEC: a uniform platform for security analysis of deep learning model. In: IEEE S&P (2019)
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)
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, pp. 2574–2582 (2016)
Papernot, N., et al.: Cleverhans v2. 0.0: an adversarial machine learning library. arXiv preprint arXiv:1610.00768 (2016)
Papernot, N., McDaniel, P., Goodfellow, I.: Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277 (2016)
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)
Shi, C., et al.: Adversarial captchas. arXiv preprint arXiv:1901.01107 (2019)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Xu, L., Zhang, D., Jayasena, N., Cavazos, J.: HADM: hybrid analysis for detection of malware. In: Bi, Y., Kapoor, S., Bhatia, R. (eds.) IntelliSys 2016. LNNS, vol. 16, pp. 702–724. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-56991-8_51
Xu, Y., et al.: Deep learning of feature representation with multiple instance learning for medical image analysis. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1626–1630. IEEE (2014)
Zhang, X., Wang, N., Shen, H., Ji, S., Luo, X., Wang, T.: Interpretable deep learning under fire. In: USENIX Security (2020)
Acknowledgements
This work was partly supported by NSFC under No. 61772466 and U1836202, the Zhejiang Provincial Natural Science Foundation for Distinguished Young Scholars under No. LR19F020003, and the Provincial Key Research and Development Program of Zhejiang, China under No. 2017C01055.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, C., Weng, H., Ji, S., Dong, J., He, Q. (2019). DeT: Defending Against Adversarial Examples via Decreasing Transferability. In: Vaidya, J., Zhang, X., Li, J. (eds) Cyberspace Safety and Security. CSS 2019. Lecture Notes in Computer Science(), vol 11982. Springer, Cham. https://doi.org/10.1007/978-3-030-37337-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-37337-5_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37336-8
Online ISBN: 978-3-030-37337-5
eBook Packages: Computer ScienceComputer Science (R0)