Adversarial Attacks on SDN-Based Deep Learning IDS System

  • Chi-Hsuan Huang
  • Tsung-Han Lee
  • Lin-huang ChangEmail author
  • Jhih-Ren Lin
  • Gwoboa Horng
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 513)


In recent years, software defined networking (SDN) has become a novel network architecture and design by employing manageable software between the control and data planes. Many SDN-based intrusion detection systems (IDS) have been proposed in recent researches. On the other hand, deep learning has emerged as an explosive growth in research and industry. The application of deep learning on IDS has been studied in many security-critical scenarios. However, some reports has indicated the vulnerability of adversarial attacks on deep learning IDS system with intentional perturbation injection or manipulation. It is important for the empowered IDS system employing deep learning to be responsible for not leading misclassification. Therefore, exploring the impact on the adversarial attacks over SDN networks or security-critical scenarios applying deep learning is an important step to confront such urgent issues. In this paper, we will conduct the SDN-based experiments on adversarial attacks for deep learning detecting system. We propose a novel class of adversarial attacks that exploits the vulnerability of the deep learning classifiers in SDN environment. Three typical deep learning models combining with four different adversarial testing will be conducted in the simulation for complete analysis.


Adversarial attacks SDN Deep learning IDS 



This research was supported by research grants (MOST 105-2221-E-142-001-MY2 and 105-2221-E-142-002-MY2) from Ministry of Science and Technology, Taiwan.


  1. 1.
    Software Defined Network [Online].
  2. 2.
  3. 3.
    Nmap [Online].
  4. 4.
    Almeida LB (1997) Multilayer perceptrons, in Handbook of Neural Computation, IOP Publishing Ltd and Oxford University PressGoogle Scholar
  5. 5.
    LeCun, Yann. LeNet-5, convolutional neural networks. Retrieved 16 November 2013 Convolutional Neural Network (CNN)Google Scholar
  6. 6.
    Sepp H, Jürgen S (1997) Long short-term memory. Neural Comput 9(8):1735–1780. PMID 9377276CrossRefGoogle Scholar
  7. 7.
    Yuan X, He P, Zhu Q, Bhat R, Li X (2017) Adversarial examples: attacks and defenses for deep learning at
  8. 8.
    Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint. arXiv:1412.6572
  9. 9.
    Papernot N, McDaniel P, Goodfellow I, Jha S, Celik ZB, Swami A (2016) Practical black-box attacks against deep learning systems using adversarial examples. arXiv preprint. arXiv:1602.02697
  10. 10.
  11. 11.
    Ryu SDN Framework [Online].
  12. 12.
    Braga R, Mota E, Passito A (2010) Lightweight DDoS flooding attack detection using NOX/OpenFlow. In: Annual IEEE conference on local computer networks, Oct. 2010Google Scholar
  13. 13.
    Mininet [Online].
  14. 14.
    Open vSwitch [Online].
  15. 15.
    Tang TA, Mhamdi L, McLernon D, Zaidi S, Ghogho M (2016) Deep learning approach for network intrusion detection in software defined networking. Wireless Networks and Mobile Communications, Oct. 2016Google Scholar
  16. 16.
    Niyaz Q, Sun W, Javaid AY (2016) A deep learning based DDOS detection system in software-defined newtoking (SDN). ArXiv:1611.07400Google Scholar
  17. 17.
    Maria Rigaki (2017) Adversarial deep learning against intrusion detection classifiers.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Chi-Hsuan Huang
    • 1
  • Tsung-Han Lee
    • 2
  • Lin-huang Chang
    • 2
    Email author
  • Jhih-Ren Lin
    • 2
  • Gwoboa Horng
    • 1
  1. 1.Department of Computer Science and EngineeringNational Chung-Hsing UniversityTaichungTaiwan
  2. 2.Department of Computer ScienceNational Taichung University of EducationTaichungTaiwan

Personalised recommendations