Principle components analysis and Support Vector Machine based Intrusion Detection System

Eid, Heba F.; Darwish, Ashraf; Hassanien, Aboul Ella; Abraham, Ajith

doi:10.1109/isda.2010.5687239

Cited by 86 publications

(34 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A deep belief network, a gain ration and a chi-square were used to select only 13 features based on the proposed work in [15]. Principal component analysis was also used in [19] to reduce the selected features to 23. The authors in [24] apply a combining classifier with NBTree and RandomTree algorithm in the NSL-KDD dataset for detecting the normal and attack traffic with an achieved accuracy of 89,24% along 41 attributes.…”

Section: Related Workmentioning

confidence: 99%

A Two-Stage Classifier Approach using RepTree Algorithm for Network Intrusion Detection

Belouch¹,

Hadaj²,

Idhammad³

2017

ijacsa

View full text Add to dashboard Cite

Abstract-In this paper, we present a two-stage classifier based on RepTree algorithm and protocols subset for network intrusion detection system. To evaluate the performance of our approach, we used the UNSW-NB15 data set and the NSL-KDD data set. In first phase our approach divides the incoming network traffics into three type of protocols TCP, UDP or Other, then classifies into normal or anomaly. In second stage a multiclass algorithm classify the anomaly detected in the first phase to identify the attacks class in order to choose the appropriate intervention. The number of features is reduced from over 40 to less than 20 features, according to the protocol, using feature selection techniques. The detection accuracy of 88,95% and 89,85% was achieved on the complete UNSW-NB15 and NSL-KDD data set, respectively using individual classifier, results are better as compared to the recent work on these data sets.

show abstract

Section: Related Workmentioning

confidence: 99%

A Two-Stage Classifier Approach using RepTree Algorithm for Network Intrusion Detection

Belouch¹,

Hadaj²,

Idhammad³

2017

ijacsa

View full text Add to dashboard Cite

show abstract

“…Heba, F.Eid in [9] has proposed a method for feature selection for anomaly intrusion detection system using PCA method. The principal components are selected on the basis of eigenvalues.…”

Section: Related Workmentioning

confidence: 99%

A Feature Selection Technique for Intrusion Detection System Based on Iwd and Aco

Haneef¹,

Singh²

2017

ijarcs

View full text Add to dashboard Cite

Rapid advancements in the internet technology and its vulnerabilities have led researchers to devise intelligent systems that can provide network security. Intrusion detection systems (IDS) scrutinize all the features to detect intrusive data. Some of the features may be redundant or irrelevant to the detection process, which results in computational complexities and increased training time. To mitigate this problem, a process known as feature selection is used to remove the redundant and irrelevant attributes of the dataset. This paper proposes an intelligent hybrid technique for the purpose of feature selection of KDD CUP'99 dataset using the concepts of metaheuristic optimization. This hybrid approach combines the concepts of Intelligent Water Drops(IWD) and Ant Colony Optimization(ACO)to select features from data. The objective of this work is to optimize the process of feature selection in order to achieve optimal feature subset and reduce the training time.

show abstract

“…In [5] Chunhua Gu and et al proposed a system using rough set for attribution reduction and support vector machine for intrusion detection classification. In [6] an Intrusion detection system has been effectively introduced by using Principal Component Analysis (PCA) as an approach to select the optimum feature subset with Support Vector Machines (SVMs) as the system classifier. An architecture proposed by employing a hybrid ANN (Artificial Neural Network) for both visualizing intrusions activities using Kohenen's SOM, and classifying intrusions using resilient propagation neural networks is presented in [7].…”

Section: Related Workmentioning

confidence: 99%

Intrusion Detection System Based on K-Star Classifier and Feature Set Reduction

2013

IOSR-JCE

View full text Add to dashboard Cite

show abstract

Principle components analysis and Support Vector Machine based Intrusion Detection System

Cited by 86 publications

References 13 publications

A Two-Stage Classifier Approach using RepTree Algorithm for Network Intrusion Detection

A Two-Stage Classifier Approach using RepTree Algorithm for Network Intrusion Detection

A Feature Selection Technique for Intrusion Detection System Based on Iwd and Aco

Intrusion Detection System Based on K-Star Classifier and Feature Set Reduction

Contact Info

Product

Resources

About