Advertisement

Adversarial attack-based security vulnerability verification using deep learning library for multimedia video surveillance

  • JaeHan Jeong
  • Sungmoon Kwon
  • Man-Pyo Hong
  • Jin Kwak
  • Taeshik ShonEmail author
Article

Abstract

Recently, although deep learning has been employed in various fields, it poses the risk of a possible adversarial attack. In this study, we experimentally verified that classification accuracy in the image classification model of deep learning is lowered by adversarial samples generated by malicious attackers. We used the MNIST dataset, a representative image sample, and the NSL-KDD dataset, a representative network data. We measured the detection accuracy by injecting adversarial samples into the Autoencoder and Convolution Neural Network (CNN) classification models created using the TensorFlow and PyTorch libraries. Adversarial samples were generated by transforming the MNIST and NSL-KDD test datasets using the Jacobian-based Saliency Map Attack (JSMA) method and Fast Gradient Sign Method (FGSM). While measuring the accuracy by injecting the samples into the classification model, we verified that the detection accuracy was reduced by a minimum of 21.82% and a maximum of 39.08%.

Keywords

Autoencoder Security Deep learning CNN MNIST NSL-KDD Adversarial attack 

Notes

Acknowledgments

- This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-2016-0-00304) supervised by the IITP (Institute for Information & communications Technology Promotion)

- This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2018R1D1A1B07043349)

- This research was supported by an IITP grant funded by the Korean government (MSIT) (No. 2018-0-00336, Advanced Manufacturing Process Anomaly Detection to prevent the Smart Factory Operation Failure by Cyber Attacks)

- This work was supported by the Ajou University research fund

References

  1. 1.
    Abadi M et al (2016) Tensorflow: a system for large-scale machine learning. In: OSDI, vol 16Google Scholar
  2. 2.
    Bottou L et al (1994) Comparison of classifier methods: a case study in handwritten digit recognition. In: Pattern recognition, 1994. Vol. 2-conference B: computer vision & image processing., proceedings of the 12th IAPR international. Conference on. Vol. 2. IEEEGoogle Scholar
  3. 3.
    Finlayson SG, Kohane IS, Beam AL (2018) Adversarial attacks against medical deep learning systems. arXiv preprint arXiv:1804.05296Google Scholar
  4. 4.
    Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572Google Scholar
  5. 5.
    Heckerman D, Meek C (1997) Models and selection criteria for regression and classification. In: Proceedings of the thirteenth conference on uncertainty in artificial intelligence. Morgan Kaufmann Publishers Inc.Google Scholar
  6. 6.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces SystGoogle Scholar
  7. 7.
    Kurakin A, Goodfellow I, Bengio S (2016) Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533Google Scholar
  8. 8.
    Papernot N et al (2016) The limitations of deep learning in adversarial settings. In: Security and privacy (EuroS&P), 2016 IEEE European symposium on. IEEEGoogle Scholar
  9. 9.
    Papernot N et al (2016) Cleverhans v2. 0.0: an adversarial machine learning library. arXiv preprint arXiv:1610.00768Google Scholar
  10. 10.
    Papernot N et al (2017) Practical black-box attacks against machine learning. In: Proceedings of the 2017 ACM on Asia conference on computer and communications security. ACMGoogle Scholar
  11. 11.
    Vincent P et al (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408MathSciNetzbMATHGoogle Scholar
  12. 12.
    Zhang G et al (2017) DolphinAttack: inaudible voice commands. In: Proceedings of the 2017 ACM SIGSAC conference on computer and communications security. ACMGoogle Scholar
  13. 13.
    KDD Cup (1999) Available on: http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html. Accessed 26 Jan 2019

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Ajou UniversitySuwon-citySouth Korea

Personalised recommendations