A Novel Hybrid IDS Based on Modified NSGAII-ANN and Random Forest

Golrang, Anahita; Golrang, Alale Mohammadi; Yayilgan, Sule Yildirim; Elezaj, Ogerta

doi:10.3390/electronics9040577

Cited by 33 publications

(10 citation statements)

References 27 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This provides a gap for further investigation. In our previous research [5], we proposed an intrusion detection framework based on a modified multi-objective feature selection approach called NSGAII.…”

Section: Feature Selectionmentioning

confidence: 99%

“…The feature selection technique aims at reducing the irrelevant features, reducing the computation cost, increase prediction performance and gaining a better understanding or representation of the data [4]. Although feature selection methods have been used widely in other fields such as intrusion detection systems [5], the majority of papers in the area of Android malware detection tend to select the essential features by rationalizing which require a deep understanding of the nature of the features involved in Android applications. The research in [2] and [6] have provided review papers on various types of features which have been applied in Android malware detection systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Multi-objective Feature Selection in Android Malware Detection System

Golrang

Yayilgan

Elezaj

2021

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

The Android operating system boasts a global market share over the previous years, which has made it the most popular operating system in the world. Recently, Android has become the target of attacks by cybercriminals because of its open-source code and its progressive growth. Many machine learning techniques have been used to address this issue in the Android operating system. However, a limited range of feature selection methods has been used in these systems. This paper, therefore, aims to address and evaluate the impact of a multi-objective feature selection approach called NSGAII in Android malware detection systems. To improve the diversity of solutions offered by this method, we have modified the standard NSGAII approach. Experimental results show that the proposed method can lead to better malware classification.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Multi-objective Feature Selection in Android Malware Detection System

Golrang

Yayilgan

Elezaj

2021

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Golrang et al [19] NSL-KDD Random Forest 99.4 Gao et al [20] Incremental extreme learning machine (I-ELM) and Adaptive principal component (A-PCA)…”

Section: Study Data Setmentioning

confidence: 99%

Intrusion Detection System Combined Enhanced Random Forest With Smote Algorithm

Fan

Zhu

et al. 2021

Preprint

View full text Add to dashboard Cite

Network security is subject to malicious attacks from multiple sources, and intrusion detection systems (IDS) play a key role in maintaining network security. During the training of intrusion detection models, the detection results generally have relatively large false detection rates due to the shortage of training data caused by data imbalance. To address the existing sample imbalance problem, this paper proposed a network intrusion detection algorithm based on enhanced random forest and Synthetic Minority Over-Sampling Technique (SMOTE) algorithm. Firstly, the method used a hybrid algorithm combining the K-means clustering algorithm with the SMOTE sampling algorithm to increase the number of minor samples and thus achieved a balanced data set, by which the sample features of minor samples could be learned more effectively. Secondly, preliminary prediction result was obtained by using enhanced random forest, and then the similarity matrix of network attacks was used to correct the prediction results of voting processing by the analysis of the type of network attacks. In this paper, the performance was tested using the NSL-KDD dataset with a classification accuracy of 99.72% on the training set and 78.47% on the test set. Compared with other related papers, our method has some improvement in the classification accuracy of detection.

show abstract

“…It contributes to analyses and handling the massive amount of data and extracts the essential features that are used in various techniques for feature selection [14]. IDS is a commonly used machine learning classifier to distinguish between various attacks as a class [15]. Many supervised classification algorithms are applied to IDS, such as Decision Trees, Naïve Bayes, K-Nearest Neighbor, Tree C4.5, Random Forest, Support Vector Machine, and Logistic Regression [16].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Classification Algorithms for Intrusion Detection System: A Review

Salih

Abdulazeez

2021

JSCDM

View full text Add to dashboard Cite

Intrusion detection is one of the most critical network security problems in the technology world. Machine learning techniques are being implemented to improve the Intrusion Detection System (IDS). In order to enhance the performance of IDS, different classification algorithms are applied to detect various types of attacks. Choosing a suitable classification algorithm for building IDS is not an easy task. The best method is to test the performance of the different classification algorithms. This paper aims to present the result of evaluating different classification algorithms to build an IDS model in terms of confusion matrix, accuracy, recall, precision, f-score, specificity and sensitivity. Nevertheless, most researchers have focused on the confusion matrix and accuracy metric as measurements of classification performance. It also provides a detailed comparison with the dataset, data preprocessing, number of features selected, feature selection technique, classification algorithms, and evaluation performance of algorithms described in the intrusion detection system.

show abstract

A Novel Hybrid IDS Based on Modified NSGAII-ANN and Random Forest

Cited by 33 publications

References 27 publications

The Multi-objective Feature Selection in Android Malware Detection System

The Multi-objective Feature Selection in Android Malware Detection System

Intrusion Detection System Combined Enhanced Random Forest With Smote Algorithm

Evaluation of Classification Algorithms for Intrusion Detection System: A Review

Contact Info

Product

Resources

About