Skip to content

Research at St Andrews

Improving intrusion detection model prediction by threshold adaptation

Research output: Contribution to journalArticle

DOI

Open Access permissions

Open

Author(s)

Amjad Mohamed Hamdan Al Tobi, Ishbel Mary Macdonald Duncan

School/Research organisations

Abstract

Network traffic exhibits a high level of variability over short periods of time. This variability impacts negatively on the accuracy of anomaly-based network intrusion detection systems (IDS) that are built using predictive models in a batch learning setup. This work investigates how adapting the discriminating threshold of model predictions, specifically to the evaluated traffic, improves the detection rates of these intrusion detection models. Specifically, this research studied the adaptability features of three well known machine learning algorithms: C5.0, Random Forest and Support Vector Machine. Each algorithm’s ability to adapt their prediction thresholds was assessed and analysed under different scenarios that simulated real world settings using the prospective sampling approach. Multiple IDS datasets were used for the analysis, including a newly generated dataset (STA2018). This research demonstrated empirically the importance of threshold adaptation in improving the accuracy of detection models when training and evaluation traffic have different statistical properties. Tests were undertaken to analyse the effects of feature selection and data balancing on model accuracy when different significant features in traffic were used. The effects of threshold adaptation on improving accuracy were statistically analysed. Of the three compared algorithms, Random Forest was the most adaptable and had the highest detection rates.
Close

Details

Original languageEnglish
Article number159
Number of pages41
JournalInformation
Volume10
Issue number5
DOIs
Publication statusPublished - 30 Apr 2019

    Research areas

  • Intrusion Detection System, Anomaly-based IDS, Threshold adaptation, Prediction accuracy improvement, Machine learning, STA2018 dataset, C5.0, Random forest, Support vector machine

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. A novel method to prevent phishing by using OCR technology

    Wang, Y. & Duncan, I. M. M., 5 Jun 2019. 5 p.

    Research output: Contribution to conferencePaper

  2. Human visual based perception of steganographic images

    Fyffe, B., Wang, Y. & Duncan, I., 2019, In : Journal of Cyber Security Technology. 3, 2, p. 61-107 47 p.

    Research output: Contribution to journalArticle

  3. KDD 1999 generation faults: a review and analysis

    Al Tobi, A. M. & Duncan, I., 2018, In : Journal of Cyber Security Technology. 2, 3-4, p. 164-200 37 p.

    Research output: Contribution to journalArticle

  4. Aerial Virtual Reality: Remote Tourism With Drones

    Fabola, A. E., Miller, A. & Duncan, I. M. M., Nov 2017.

    Research output: Contribution to conferencePaper

  5. Aerial Virtual Reality: remote tourism with drones

    Fabola, A. E., Miller, A. H. D. & Duncan, I. M. M., 16 Oct 2017, Journal of Immersive Education: E-iED 2017, Proceedings. Immersive Education Initiative, 13 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

ID: 258834046