skip to main content
10.1145/3240765.3274525guideproceedingsArticle/Chapter ViewAbstractPublication PagesConference Proceedingsacm-pubtype
research-article

Assured Deep Learning: Practical Defense Against Adversarial Attacks

Published: 05 November 2018 Publication History

Abstract

Deep Learning (DL) models have been shown to be vulnerable to adversarial attacks. In light of the adversarial attacks, it is critical to reliably quantify the confidence of the prediction in a neural network to enable safe adoption of DL models in autonomous sensitive tasks (e.g., unmanned vehicles and drones). This article discusses recent research advances for unsupervised model assurance against the strongest adversarial attacks known to date and quantitatively compare their performance. Given the widespread usage of DL models, it is imperative to provide model assurance by carefully looking into the feature maps automatically learned within D1 models instead of looking back with regret when deep learning systems are compromised by adversaries.

References

[1]
S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard, “Deepfool: a simple and accurate method to fool deep neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
[2]
N. Carlini and D. Wagner, “Towards evaluating the robustness of neural networks,” in Security and Privacy (SP), 2017 IEEE Symposium on. IEEE, 2017.
[3]
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus, “Intriguing properties of neural networks,” arXiv preprint arXiv:, 2013.
[4]
D. Meng and H. Chen, “Magnet: a two-pronged defense against adversarial examples,” in Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. ACM, 2017.
[5]
S. Shen, G. Jin, K. Gao, and Y. Zhang, “Ape-gan: Adversarial perturbation elimination with gan,” ICLR Submission, available on OpenReview, 2017.
[6]
X. Ma, B. Li, Y. Wang, S.M. Erfani, S. Wijewickrema, M.E. Houle, G. Schoenebeck, D. Song, and J. Bailey, “Characterizing adversarial subspaces using local intrinsic dimensionality,” arXiv preprint arXiv:, 2018.
[7]
F. Tramèr, A. Kurakin, N. Papernot, I. Goodfellow, D. Boneh, and P. Mc-Daniel, “Ensemble adversarial training: Attacks and defenses” arXiv preprint arXiv:, 2017.
[8]
N. Papernot, P. McDaniel, X. Wu, S. Jha, and A. Swami, “Distillation as a defense to adversarial perturbations against deep neural networks,” 2016.
[9]
S. Gu and L. Rigazio, “Towards deep neural network architectures robust to adversarial examples,” arXiv preprint arXiv:, 2014.
[10]
B. Rouhani, M. Samragh, M. Javaheripi, T. Javidi, and F. Koushanfar, “Deepfense: Online accelerated defense against adversarial deep learning,” 2018.
[11]
B. Rouhani, M. Samragh, T. Javidi, and F. Koushanfar, “Safe machine learning and defeating adversarial attacks,” 2018.
[12]
J. Tropp, A.C. Gilbert et al., “Signal recovery from random measurements via orthogonal matching pursuit,” IEEE Transactions on Information Theory, vol. 53, no. 12, pp. 4655–4666, 2007.
[13]
K. Grosse, P. Manoharan, N. Papernot, M. Backes, and P. McDaniel, “On the (statistical) detection of adversarial examples,” arXiv preprint arXiv:, 2017.
[14]
R. Feinman, R.R. Curtin, S. Shintre, and A.B. Gardner, “Detecting adversarial samples from artifacts,” arXiv preprint arXiv:, 2017.
[15]
A. Kurakin, I. Goodfellow, and S. Bengio, “Adversarial examples in the physical world,” arXiv preprint arXiv:, 2016.
[16]
N. Carlini and D. Wagner, “Magnet and“efficient defenses against adversarial attacks” are not robust to adversarial examples” arXiv preprint arXiv:, 2017.
[17]
V. Zantedeschi, M.-I. Nicolae, and A. Rawat, “Efficient defenses against adversarial attacks,” in Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security. ACM, 2017.

Index Terms

  1. Assured Deep Learning: Practical Defense Against Adversarial Attacks
        Index terms have been assigned to the content through auto-classification.

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image Guide Proceedings
        2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
        Nov 2018
        939 pages

        Publisher

        IEEE Press

        Publication History

        Published: 05 November 2018

        Permissions

        Request permissions for this article.

        Qualifiers

        • Research-article

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • 0
          Total Citations
        • 188
          Total Downloads
        • Downloads (Last 12 months)0
        • Downloads (Last 6 weeks)0
        Reflects downloads up to 19 Feb 2025

        Other Metrics

        Citations

        View Options

        View options

        Figures

        Tables

        Media

        Share

        Share

        Share this Publication link

        Share on social media