Advertisement

Towards Machine Learning Based IoT Intrusion Detection Service

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10868)

Abstract

IoT Security is one of the most critical issues when developing, implementing and deploying IoT platforms. IoT refers to the ability of communication, monitoring and remote control of automated devices through the internet. Due to low computational capabilities, less power, and constrained technologies, IoT is vulnerable to various cyber attacks. Security mechanisms such as cryptography and authentication are hard to apply due to the aforementioned constraints on IoT devices. To overcome this issue Intrusion Detection Systems (IDSs) play main role as a high-security solution. This paper shows a proposed IDS based on machine learning techniques to be implemented into IoT platforms as a service. We used Random forest as a classifier to detect intrusions, then we applied neural network classifier to detect the categorization of the detected intrusion. The experimental results showed the proposed model can effectively detect intrusions, yet categorization of the intrusion suffers from low accuracy and high bias.

Keywords

Anomaly detection Neural network IoT security IDS 

References

  1. 1.
    Moustafa, N., Slay, J.: UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: 2015 Military Communications and Information Systems Conference (MilCIS). IEEE (2015)Google Scholar
  2. 2.
    Suo, H., Wan, J., Zou, C., Liu, J.: Security in the Internet of Things: a review. In: International Conference on Computer Science and Electronics Engineering (ICCSEE), vol. 3 (2012)Google Scholar
  3. 3.
    Pacheco, J., Hariri, S.: IoT security framework for smart cyber infrastructures. In: 1st International Workshops on Foundations and Applications of Self Systems (2016)Google Scholar
  4. 4.
    Aircrack-ng tools for Wifi network security. https://www.aircrack-ng.org/
  5. 5.
    OWASP IoT Testing Guidance. https://owasp.org
  6. 6.
    Hodo, E., Bellekens, X., Hamilton, A., Tachtatzis, C., Atkinson, R.: Shallow and deep networks intrusion detection system: a taxonomy and survey (2017)Google Scholar
  7. 7.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar
  8. 8.
    ITKST42: information security technology course. https://github.com/Moskari/ITKST42-network-data-classifier
  9. 9.
    Matthew, V., Philip, K.: PHAD: packet header anomaly detection for identifying hostile network traffic. Department of Computer Sciences Florida Institute of Technology Technical report CS-2001-04 (2001)Google Scholar
  10. 10.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, San Francisco (2005)MATHGoogle Scholar
  11. 11.
    de Lima, I.V.M., Degaspari, J.A., Sobral, J.B.M.: Intrusion detection through artificial neural networks. In: Network Operations and Management Symposium NOMS 2008, pp. 867–870. IEEE, 7–11 April 2008Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceNagoya Institute of TechnologyNagoyaJapan

Personalised recommendations