Dimensionality reduction with IG-PCA and ensemble classifier for network intrusion detection

Salo, Fadi; Nassif, Ali Bou; Essex, Aleksander

doi:10.1016/j.comnet.2018.11.010

Cited by 252 publications

(125 citation statements)

References 35 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…The experiment on NSL-KDD dataset indicates that the highest accuracy obtained when using RF and PART as base classifiers under the product probability rule. In addition, Salo et al [77] proposed a hybrid IDS which combines the feature selection approaches of IG and Principal Component Analysis (PCA) with an ensemble classifier based on Support Vector Machine (SVM), Instance-Based learning algorithms (IBK), and Multi-Layer Perceptron (MLP). A comparative analysis performed on several IDS datasets has proven that IG-PCA-Ensemble method exhibits better performance than the majority of existing approaches.…”

Section: On Hybrid Approachesmentioning

confidence: 99%

“…Modern intrusion detection datasets inevitably contain plenty of redundant and irrelevant attributes [2], which lower the efficacy of data mining algorithms and cause uninterpretable results [21]. Therefore, the first step in this study is to reduce the dimensionality and select the feature subset of the utilized dataset [77]. In this paper, a hybrid approach by combining CFS with BA is proposed to optimize the efficiency of the feature selection process and enhance the accuracy of the classification.…”

Section: Feature Selectionmentioning

confidence: 99%

“…Likewise, ensemble methods have been shown to improve accuracy in many use cases, including intrusion detection. For example, the results in [1,72,77] proved that their proposed ensemble models produce better performance of IDS than the one using a single classifier. For security professionals, ensemble classifiers provide mechanisms that aid in analysis such as similarity to existing known malicious or benign samples.…”

Section: Ensemble Classificationmentioning

confidence: 99%

“…There was one problem with the initial idea of applying ML in IDS, that is, a single classifier may not be strong enough to build a good IDS. Thus, researchers have come up with the idea of constructing ensemble classifiers for IDSs [28,77]. In general, the main goal of ensemble learning is to combine a set of individual classifiers and then make a better classification decision about the object submitted at the input [72].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Building an efficient intrusion detection system based on feature selection and ensemble classifier

et al. 2020

View full text Add to dashboard Cite

A B S T R A C T Intrusion detection system (IDS) is one of extensively used techniques in a network topology to safeguard the integrity and availability of sensitive assets in the protected systems. Although many supervised and unsupervised learning approaches from the field of machine learning have been used to increase the efficacy of IDSs, it is still a problem for existing intrusion detection algorithms to achieve good performance. First, lots of redundant and irrelevant data in high-dimensional datasets interfere with the classification process of an IDS. Second, an individual classifier may not perform well in the detection of each type of attacks. Third, many models are built for stale datasets, making them less adaptable for novel attacks. Thus, we propose a new intrusion detection framework in this paper, and this framework is based on the feature selection and ensemble learning techniques. In the first step, a heuristic algorithm called CFS-BA is proposed for dimensionality reduction, which selects the optimal subset based on the correlation between features. Then, we introduce an ensemble approach that combines C4.5, Random Forest (RF), and Forest by Penalizing Attributes (Forest PA) algorithms. Finally, voting technique is used to combine the probability distributions of the base learners for attack recognition. The experimental results, using NSL-KDD, AWID, and CIC-IDS2017 datasets, reveal that the proposed CFS-BA-Ensemble method is able to exhibit better performance than other related and state of the art approaches under several metrics.

show abstract

Section: On Hybrid Approachesmentioning

confidence: 99%

Section: Feature Selectionmentioning

confidence: 99%

Section: Ensemble Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Building an efficient intrusion detection system based on feature selection and ensemble classifier

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Several researchers have been working in the field of NIDS techniques through ML approaches from last few decades [2]. In view of the wide usage of cloud, the malicious activities are also increased in the cloud environment so the researchers also developed defense mechanisms from the last decade.…”

Section: Related Workmentioning

confidence: 99%

A Novel Framework for NIDS Throuh Fast Knn Classifier on CICIDS 2017 Dataset

Krishna¹,

Swathi²,

Rao³

2020

IJRTE

View full text Add to dashboard Cite

This paper investigates the performance of a Fast kNearest Neighbor Classifier (FkNN) for Network Intrusion Detection System (NIDS) on Cloud Environment. For this study Variance Index based Partial Distance Search (VIPDS) kNN [7] is adopted as an FkNN classifier. A benchmark dataset CICIDS2017[16] is considered for the evaluation process because it is a 78 featured dataset with most updated cloud related attacks. To achieve this objective a frame work is proposed for implementing FkNN and compared with kNN classifier by considering two performance measures Accuracy and computational time. This study explores the gain in the computational time without compromising the Accuracy while using FkNN instead of kNN over a large featured dataset. The conclusions are drawn as per the results obtained from the experiments conducted on CICIDS2017 dataset.

show abstract

An intrusion detection algorithm based on bag representation with ensemble support vector machine in cloud computing

Wei

Long

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

The increase of security incidents brings a challenge to the cloud computing security. Intrusion detection technologies have been applied to protect information in cloud from being compromised, and complicated learning-based detection methods have been used to improve the performance of intrusion detection systems. Higher quality and well-formed samples are crucial to the performance of detection algorithm. Therefore, we mainly study the intrusion detection model based on data optimization processing. In this article, we establish an intrusion detection algorithm based on ensemble support vector machine with bag representation. Specifically, the sample flows are divided into bags, where the sample flows in each bag are related to each other. Each bag contains multiple related data flows that can accurately reflect intrusion behavior, especially persistent intrusion. What's more, ensemble algorithm is applied to detection model, which greatly optimizes the performance of detection algorithm. The experimental results on open access datasets show that the proposed model detects the persistent attack with 90.58% recall.

show abstract

Dimensionality reduction with IG-PCA and ensemble classifier for network intrusion detection

Cited by 252 publications

References 35 publications

Building an efficient intrusion detection system based on feature selection and ensemble classifier

Building an efficient intrusion detection system based on feature selection and ensemble classifier

A Novel Framework for NIDS Throuh Fast Knn Classifier on CICIDS 2017 Dataset

An intrusion detection algorithm based on bag representation with ensemble support vector machine in cloud computing

Contact Info

Product

Resources

About