skip to main content
10.1145/3436369.3436457acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccprConference Proceedingsconference-collections
research-article

An Optimized Algorithm for Speeding up Universal Adversarial Perturbation Generation

Published: 11 January 2021 Publication History

Abstract

Universal adversarial perturbation, which is a security vulnerability in convolutional neural networks (CNNs), can fool convolutional neural network models on a set of images by a single perturbation vector. One recent algorithm, named UAP, generates universal adversarial perturbation iteratively by aggregating the smallest adversarial perturbations with respect to each image, but it ignored the orientations of perturbation vectors; consequently, the magnitude of the universal adversarial perturbation cannot efficiently increase at each iteration, thereby resulting in slow universal adversarial perturbation generation. Hence, to expedite the generation of universal adversarial perturbation, we propose an optimized algorithm to generate universal adversarial perturbation based on the orientations of perturbation vectors and aggregate adversarial perturbations with similar orientations. The proposed algorithm is compared with the original algorithm on ImageNet dataset, experimental results show that our proposed algorithm is more efficient and can reduce the number of training images compared with the UAP with nearly the same fooling rate.

References

[1]
Krizhevsky, A., Sutskever, I., and Hinton, G. E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 2012: 1097--1105.
[2]
Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. 2017. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117--2125.
[3]
Zhang, Y., Zhao, D., Sun, J., Zou, G., and Li, W. 2016. Adaptive convolutional neural network and its application in face recognition. Neural Processing Letters. 2016, 43(2):389--399.
[4]
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. 2013. Intriguing properties of neural networks. arXiv preprint arXiv: 1312.6199.
[5]
Moosavi-Dezfooli, S. M., Fawzi, A., Fawzi, O., and Frossard, P. 2017. Universal adversarial perturbations. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1765--1773.
[6]
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., and Fei-Fei, L. 2009, June. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. 2009: 248--255.
[7]
Goodfellow, I. J., Shlens, J., and Szegedy, C. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.
[8]
Rozsa, A., Rudd, E. M., and Boult, T. E. 2016. Adversarial diversity and hard positive generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2016: 25--32.
[9]
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., and McDaniel, P. 2017. Ensemble adversarial training: Attacks and defenses. arXiv preprint arXiv:1705.07204.
[10]
Moosavi-Dezfooli, S. M., Fawzi, A., and Frossard, P. 2016. Deepfool: a simple and accurate method to fool deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2574--2582.
[11]
Reddy Mopuri, K., Krishna Uppala, P., and Venkatesh Babu, R. 2018. Ask, acquire, and attack: Data-free uap generation using class impressions. In Proceedings of the European Conference on Computer Vision (ECCV). 2018: 19--34.
[12]
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. 2017. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700--4708.
[13]
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... and Rabinovich, A. 2015. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1--9.
[14]
Simonyan, K., and Zisserman, A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv.1409.1556.
[15]
He, K., Zhang, X., Ren, S., and Sun, J. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770--778.

Index Terms

  1. An Optimized Algorithm for Speeding up Universal Adversarial Perturbation Generation

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICCPR '20: Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition
    October 2020
    552 pages
    ISBN:9781450387835
    DOI:10.1145/3436369
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    In-Cooperation

    • Beijing University of Technology

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 11 January 2021

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Deep learning
    2. convolutional neural network (CNN)
    3. image classification
    4. universal adversarial perturbation

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICCPR 2020

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 33
      Total Downloads
    • Downloads (Last 12 months)3
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media