An anomaly-based intrusion detection system in presence of benign outliers with visualization capabilities
- Submitting institution
-
University of East London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 25
- Type
- D - Journal article
- DOI
-
10.1016/j.eswa.2018.04.038
- Title of journal
- Expert Systems with Applications
- Article number
- -
- First page
- 36-60
- Volume
- 108
- Issue
- -
- ISSN
- 0957-4174
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
0
- Research group(s)
-
1 - Intelligent Systems
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- There have been no inspiring visualization-based IDS to propose all the possible knowledge required for intrusion detection purposes with less computational costs. In this work, we developed and designed a hybrid intelligent system with visualization capabilities. End users can see the results of anomaly detection from new monitoring data graphically together with the numerical results for classification accuracy rather than sending a massive number of alerts to administrators. Several network traffics (NSL-KDD, UNSW-NB15, AAGM and VPN-nonVPN) were evaluated to confirm the system accuracy. The results impacted the state-of-the-art for visualization capabilities in IDS opening new directions for further works.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -