UPM Institutional Repository

Adaptive feature selection for denial of services (DoS) attack


Citation

Yusof, Ahmad Riza'ain and Udzir, Nur Izura and Selamat, Ali and Hamdan, Hazlina and Abdullah @ Selimun, Mohd Taufik (2017) Adaptive feature selection for denial of services (DoS) attack. In: 2017 IEEE Conference on Application, Information and Network Security (AINS), 13-14 Nov. 2017, Miri Marriott Resort & Spa, Miri, Sarawak. (pp. 81-84).

Abstract

Adaptive detection is the learning ability to detect any changes in patterns in intrusion detection systems. In this paper, we propose combining two techniques in feature selection algorithm, namely consistency subset evaluation (CSE) and DDoS characteristic features (DCF) to identify and select the most important and relevant features related DDoS attacks. The proposed technique is trained and tested using the NSL-KDD 2009 dataset and compared with the traditional features selection method such as Information Gain, Gain Ratio, Chi-squared and Correlated features selection (CFS). The result shows that the combined CSE with DCF model overcomes the drawback of traditional feature selection technique such as avoid over-fitting, long training time and improved efficiency of detections. The adaptive model based on this technique can reduce computational complexity to analyze the data when attack occurs.


Download File

[img]
Preview
Text (Abstract)
Adaptive feature selection for denial of services (DoS) attack.pdf

Download (34kB) | Preview

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Computer Science and Information Technology
DOI Number: https://doi.org/10.1109/AINS.2017.8270429
Publisher: IEEE
Keywords: NSL-KDD; Features selection; Intrusion detection; Machine learning
Depositing User: Nabilah Mustapa
Date Deposited: 07 Mar 2018 02:14
Last Modified: 07 Mar 2018 02:14
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1109/AINS.2017.8270429
URI: http://psasir.upm.edu.my/id/eprint/59480
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item