Abstract
Deep neural networks (DNNs) have achieved performance on classical artificial intelligence problems including visual recognition, natural language processing. Unfortunately, recent studies show that machine learning models are suffering from adversarial attacks, resulting in incorrect outputs in the form of purposeful distortions to inputs. For images, such subtle distortions are usually hard to be perceptible, yet they successfully fool machine learning models. In this paper, we propose a strategy, FeaturePro, for defending machine learning models against adversarial examples and evaluating the security of deep learning system. We tackle this challenge by reducing the visible feature space for adversary. By performing white-box attacks, black-box attacks, targeted attacks and non-targeted attacks, the security of deep learning algorithms which is an important indicator for evaluating artificial intelligence systems can be evaluated. We analyzed the generalization and robustness when it is composed with adversarial training. FeaturePro has efficient defense against adversarial attacks with a high accuracy and low false positive rates.
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
Montavon, G., Samek, W., Müller, K.: Methods for interpreting and understanding deep neural networks. Digital Signal Process. 73, 1–15 (2017)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)
Papernot, N., et al.: Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks. In: 2016 IEEE Symposium on Security and Privacy (SP), pp. 582–597. IEEE (2015)
Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)
Gu, S., Rigazio, L.: Towards deep neural network architectures robust to adversarial examples. arXiv preprint arXiv:1412.5068 (2014)
Papernot, N., Mcdaniel, P.: On the effectiveness of defensive distillation. arXiv preprint arXiv:1607.05113 (2016)
Moosavi-Dezfooli, S.M., et al.: Universal adversarial perturbations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1765–1773. IEEE (2017)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2015)
Papernot, N., et al.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016)
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)
Liu, Y., et al.: Delving into transferable adversarial examples and black-box attacks. arXiv preprint arXiv:1611.02770 (2016)
Su, J., Vargas, D.V., Kouichi, S.: One pixel attack for fooling deep neural networks. IEEE Trans. Evol. Comput. 23(5), 828–841 (2017)
Sarkar, S., et al.: UPSET and ANGRI: Breaking high performance image classifiers. arXiv preprint arXiv:1707.01159 (2017)
Mardani, M., et al.: Deep generative adversarial networks for compressed sensing automates MRI. arXiv preprint arXiv:1706.0005 (2017)
Akhtar, N., Liu, J., Mian, A.: Defense against universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3389–3398 (2017)
Lee, H., Han, S., Lee, J.: Generative adversarial trainer: defense to adversarial perturbations with GAN. arXiv preprint arXiv:1705.03387 (2017)
Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354–359 (2017)
Sankaranarayanan, S., et al.: Regularizing deep networks using efficient layerwise adversarial training. arXiv preprint arXiv:1705.07819 (2017)
Li, B., Sim, K.C.: Improving robustness of deep neural networks via spectral masking for automatic speech recognition. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 279–284. IEEE (2013)
Bhagoji, A.N., et al.: Enhancing robustness of machine learning systems via data transformations. In: 2018 52nd Annual Conference on Information Sciences and Systems (CISS), pp. 1–5. IEEE (2017)
Das, N., et al.: Keeping the bad guys out: protecting and vaccinating deep learning with jpeg compression. arXiv preprint arXiv:1705.02900 (2017)
Shen, S., et al.: APE-GAN: Adversarial perturbation elimination with gan. arXiv preprint arXiv:1707.05474 (2017)
Zantedeschi, V., Nicolae, M.I., Rawat, A.: Efficient defenses against adversarial attacks. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 39–49 (2017)
Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: a survey. IEEE Access 6, 14410–14430 (2018)
Smith, L., Gal, Y.: Understanding measures of uncertainty for adversarial example detection. arXiv preprint arXiv:1803.08533 (2018)
Dumont, B., Maggio, S., Montalvo, P.: Robustness of Rotation-Equivariant Networks to Adversarial Perturbations. arXiv preprint arXiv:1802.06627 (2018)
Acknowledgments
The authors are highly thankful for National Key Research Program (2019YFB1706001), National Natural Science Foundation of China (61773001), Industrial Internet Innovation Development Project (TC190H468).
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
Pang, N., Hong, S., Pan, Y., Ji, Y. (2020). Efficient Defense Against Adversarial Attacks and Security Evaluation of Deep Learning System. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12487. Springer, Cham. https://doi.org/10.1007/978-3-030-62460-6_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-62460-6_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62459-0
Online ISBN: 978-3-030-62460-6
eBook Packages: Computer ScienceComputer Science (R0)