Learning is never secure: Poison learning by Intrusion Detection System based on Self-Organizing Map

Rupam Kumar Sharma, Hemanta Kumar Kalita, S Das, Biju Issac

    Research output: Contribution to conferencePaper

    Abstract

    Machine learning has proven to enhance the detection rate by any Intrusion Detection Engine. However, if learning is tampered than there is a likeliness that the entire detection engine might fail. This paper explores the adversary learning by SOM (Self Organizing Map) trained on NSL-KDD data set. Experimental results demonstrate the deviation of the learning behaviour after being trained with crafted poison packets to mislead the learning.
    Original languageEnglish
    Publication statusPublished - 24 Dec 2016
    Event5th IEEE-EDS International Conference on Computing, Communication and Sensor Network - Kolkata, India
    Duration: 24 Dec 201625 Dec 2016

    Conference

    Conference5th IEEE-EDS International Conference on Computing, Communication and Sensor Network
    Abbreviated titleCCSN 2016
    CountryIndia
    CityKolkata
    Period24/12/1625/12/16

    Fingerprint Dive into the research topics of 'Learning is never secure: Poison learning by Intrusion Detection System based on Self-Organizing Map'. Together they form a unique fingerprint.

  • Cite this

    Sharma, R. K., Kalita, H. K., Das, S., & Issac, B. (2016). Learning is never secure: Poison learning by Intrusion Detection System based on Self-Organizing Map. Paper presented at 5th IEEE-EDS International Conference on Computing, Communication and Sensor Network, Kolkata, India.