Using feature selection for intrusion detection system
Date
2012
Authors
Alazab, Ammar
Hobbs, Michael
Abawajy, Jemal
Alazab, Mamoun
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE Communications Society
Abstract
A good intrusion system gives an accurate and efficient classification results. This ability is an essential functionality to build an intrusion detection system. In this paper, we focused on using various training functions with feature selection to achieve high accurate results. The data we used in our experiments are NSL-KDD. However, the training and testing time to build the model is very high. To address this, we proposed feature selection based on information gain, which can contribute to detect several attack types with high accurate result and low false rate. Moreover, we performed experiments to classify each of the five classes (normal, probe, denial of service (DoS), user to super-user (U2R), and remote to local (R2L). Our proposed outperform other state-of-art methods.
Description
Keywords
Keywords: Classification results; Denial of Service; Information gain; Intrusion Detection Systems; security; State-of-art methods; Training and testing; Training function; Computer crime; Experiments; Feature extraction; Information technology; Websites; Intrusion Anomaly base detection; Feature selection; Intrusion detection; security
Citation
Collections
Source
Type
Conference paper
Book Title
Entity type
Access Statement
License Rights
DOI
10.1109/ISCIT.2012.6380910
Restricted until
2037-12-31