Skip to main content
Springer Nature Link
Log in

A Method Against Adversarial Attacks to Enhance the Robustness of Deep Learning Models

  • Conference paper
  • First Online:
Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14376))

  • 406 Accesses

Abstract

Deep learning is facing a dangerous challenge because attackers are always lurking to find and exploit the model’s vulnerabilities to deceive, making the model misidentify the classifier for the target model. It is dangerous if a smart device using artificial intelligence misrecognizes the object class. Attackers today often use adversarial examples, which at first glance do not differ from an image that is defined as natural when collected from sensors, or digital devices. Many studies on attacks and methods of combating these attacks have been tested by research groups and announced to be highly effective against attack or pattern recognition. Training the model with the aim of making the model able to recognize the adversarial example, a seemingly simple but effective method to make the model more robust, and capable of classification and identification. In this paper, to enhance the robustness of the model, the authors use adversarial training and experiment on the YOLOv7 model. Experiments show that this method is effective, making the model more powerful, capable of detecting and classifying adversarial examples after the model has been adversarial trained.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bastani, O., Ioannou, Y., Lampropoulos, L., Vytiniotis, D., Nori, A., Criminisi, A.: Measuring neural net robustness with constraints. In: Advances in Neural Information Processing Systems, vol. 29 (2016)

    Google Scholar 

  2. Bhagoji, A.N., Cullina, D., Mittal, P.: Dimensionality reduction as a defense against evasion attacks on machine learning classifiers. arXiv preprint arXiv:1704.02654, vol. 2, no. 1 (2017)

  3. Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H.P., Schölkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22(14), e49–e57 (2006)

    Article  Google Scholar 

  4. Carlini, N., Wagner, D.: Adversarial examples are not easily detected: bypassing ten detection methods. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 3–14 (2017)

    Google Scholar 

  5. 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)

    Google Scholar 

  6. Feinman, R., Curtin, R.R., Shintre, S., Gardner, A.B.: Detecting adversarial samples from artifacts. arXiv preprint arXiv:1703.00410 (2017)

  7. Gong, Z., Wang, W., Ku, W.S.: Adversarial and clean data are not twins. arXiv preprint arXiv:1704.04960 (2017)

  8. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)

  9. Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(1), 723–773 (2012)

    MathSciNet  MATH  Google Scholar 

  10. Grosse, K., Manoharan, P., Papernot, N., Backes, M., McDaniel, P.: On the (statistical) detection of adversarial examples. arXiv preprint arXiv:1702.06280 (2017)

  11. Gu, S., Rigazio, L.: Towards deep neural network architectures robust to adversarial examples. arXiv preprint arXiv:1412.5068 (2014)

  12. Hendrycks, D., Gimpel, K.: Early methods for detecting adversarial images. arXiv preprint arXiv:1608.00530 (2016)

  13. Huang, R., Xu, B., Schuurmans, D., Szepesvári, C.: Learning with a strong adversary. arXiv preprint arXiv:1511.03034 (2015)

  14. Jin, J., Dundar, A., Culurciello, E.: Robust convolutional neural networks under adversarial noise. arXiv preprint arXiv:1511.06306 (2015)

  15. Li, X., Li, F.: Adversarial examples detection in deep networks with convolutional filter statistics. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5764–5772 (2017)

    Google Scholar 

  16. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  17. Liu, X., et al.: Privacy and security issues in deep learning: a survey. IEEE Access 9, 4566–4593 (2020)

    Article  Google Scholar 

  18. Metzen, J.H., Genewein, T., Fischer, V., Bischoff, B.: On detecting adversarial perturbations. arXiv preprint arXiv:1702.04267 (2017)

  19. Nedic, B.: Gartner’s top strategic technology trends (2019)

    Google Scholar 

  20. Ni, J., Chen, Y., Chen, Y., Zhu, J., Ali, D., Cao, W.: A survey on theories and applications for self-driving cars based on deep learning methods. Appl. Sci. 10(8), 2749 (2020)

    Article  Google Scholar 

  21. 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)

    Google Scholar 

  22. Rozsa, A., Rudd, E.M., Boult, T.E.: Adversarial diversity and hard positive generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 25–32 (2016)

    Google Scholar 

  23. Shaham, U., Yamada, Y., Negahban, S.: Understanding adversarial training: increasing local stability of neural nets through robust optimization. arXiv preprint arXiv:1511.05432 (2015)

  24. Shen, F., Zhao, X., Kou, G., Alsaadi, F.E.: A new deep learning ensemble credit risk evaluation model with an improved synthetic minority oversampling technique. Appl. Soft Comput. 98, 106852 (2021)

    Article  Google Scholar 

  25. Tran, K.A., Kondrashova, O., Bradley, A., Williams, E.D., Pearson, J.V., Waddell, N.: Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Med. 13(1), 1–17 (2021)

    Article  Google Scholar 

  26. Van Huong, P., Hua, T.Q., Minh, N.H., et al.: Feature generation by k-means for convolutional neural network in detecting IoT system attacks. In: 2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), pp. 1–5. IEEE (2021)

    Google Scholar 

  27. Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464–7475 (2023)

    Google Scholar 

  28. Wang, D., Su, J., Yu, H.: Feature extraction and analysis of natural language processing for deep learning english language. IEEE Access 8, 46335–46345 (2020)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Academy of Cryptography Techniques, Ha Noi, Vietnam

    Phi Ho Truong & Duy Trung Pham

Authors
  1. Phi Ho Truong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Duy Trung Pham
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Duy Trung Pham .

Editor information

Editors and Affiliations

  1. Osaka Metropolitan University, Sakai, Osaka, Japan

    Katsuhiro Honda

  2. Vietnam National University, Ho Chi Minh City, Vietnam

    Bac Le

  3. Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan

    Van-Nam Huynh

  4. Osaka University, Toyonaka, Osaka, Japan

    Masahiro Inuiguchi

  5. Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan

    Youji Kohda

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Truong, P.H., Pham, D.T. (2023). A Method Against Adversarial Attacks to Enhance the Robustness of Deep Learning Models. In: Honda, K., Le, B., Huynh, VN., Inuiguchi, M., Kohda, Y. (eds) Integrated Uncertainty in Knowledge Modelling and Decision Making. IUKM 2023. Lecture Notes in Computer Science(), vol 14376. Springer, Cham. https://doi.org/10.1007/978-3-031-46781-3_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-46781-3_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-46780-6

  • Online ISBN: 978-3-031-46781-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics