Network Intrusion Detection Leveraging Machine Learning and Feature Selection

Ali, Asjad; Shaukat, Shahtaj; Tayyab, Muhammad; Khan, Muazzam A.; Khan, Jan Sher; Ali, Arshad; Ahmad, Jawad

doi:10.1109/honet50430.2020.9322813

Cited by 19 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21] , they used a novel method for selecting a relevant feature from an Intrusion Detection dataset to reduce the complexity, a correlation-based feature selection, and a classifier subsetevaluation approach. Then, two famous classifiers were applied to the minimized dataset: Multilayer Perceptron (MLP) and Instance-Based Learning (IBK) algorithms.…”

Section: Related Workmentioning

confidence: 99%

Obfuscated Malware Memory Detection Employing Lazy Instance Based Learner Algorithm Based On Manhattan Distance Function

Sabah Talabani,

Abdulhadi,

Ali

2024

PJBAS

View full text Add to dashboard Cite

Malware is a severe threat to the network and host system security. It is frequently the primary cause of many events, such as Distributed Denial-of-Service attacks (DDoS), spam emails, etc. The detection and elimination of Malware are the subjects of intensive study. As a result, many antivirus programs have been created to help identify and remove Malware. The issue with this antivirus software is that it uses an obsolete method of detecting Malware, the signature-matching approach, which the primary forms of code obfuscation may deceive. Since then, this has resulted in the creation of a new generation of metamorphic and polymorphic Malware. In this paper, we investigated using the Instance-Based Learner (IBK) algorithm for detecting obfuscated Malware in a given dataset. Utilizing the Lazy IBK technique in malware detection is beneficial because the algorithm can accurately detect and classify the obfuscated Malware in the dataset using the Manhattan Distance function, one of the most well-known distance metric functions for measuring the distance between points. We analyzed an obfuscated malware dataset of 58,596 records selected from 3 malware categories. The algorithm was illustrated on the dataset utilizing 10-fold cross-validation. The results demonstrate that the proposed algorithm can quickly and accurately detect obfuscated Malware with an accuracy of 99.99%, a precision of 100%, and a recall of 100%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Obfuscated Malware Memory Detection Employing Lazy Instance Based Learner Algorithm Based On Manhattan Distance Function

Sabah Talabani,

Abdulhadi,

Ali

2024

PJBAS

View full text Add to dashboard Cite

show abstract

“…Feature selection is the primary technique for data dimensionality reduction [16]; it works by selecting a subset of features that substantially contribute to the target class, thus increasing the overall predictive power of the classifier [17] and reduces the duration of the entire process as well as the computational cost [18]. Reference [18] have shown that when the dimension of features is reduced, ML techniques displayed an improved performance.…”

Section: Feature Selectionmentioning

confidence: 99%

A Machine Learning Method for Classification of Cervical Cancer

et al. 2022

View full text Add to dashboard Cite

Cervical cancer is one of the leading causes of premature mortality among women worldwide and more than 85% of these deaths are in developing countries. There are several risk factors associated with cervical cancer. In this paper, we developed a predictive model for predicting the outcome of patients with cervical cancer, given risk patterns from individual medical records and preliminary screening. This work presents a decision tree (DT) classification algorithm to analyze the risk factors of cervical cancer. Recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) feature selection techniques were fully explored to determine the most important attributes for cervical cancer prediction. The dataset employed here contains missing values and is highly imbalanced. Therefore, a combination of under and oversampling techniques called SMOTETomek was employed. A comparative analysis of the proposed model has been performed to show the effectiveness of feature selection and class imbalance based on the classifier’s accuracy, sensitivity, and specificity. The DT with the selected features from RFE and SMOTETomek has better results with an accuracy of 98.72% and sensitivity of 100%. DT classifier is shown to have better performance in handling classification problems when the features are reduced, and the problem of high class imbalance is addressed.

show abstract

“…1. An increasing number of intelligent systems are based on IoT, and securing these systems is a significant challenge [6][7][8][9][10]. In the current literature, cyber attack detection strategies for smart systems have been shown to be of great value.…”

Section: Introductionmentioning

confidence: 99%

Voting Classifier and Metaheuristic Optimization for Network Intrusion燚etection

Khafaga¹,

Karim²,

Abdelhamid³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Managing physical objects in the network's periphery is made possible by the Internet of Things (IoT), revolutionizing human life. Open attacks and unauthorized access are possible with these IoT devices, which exchange data to enable remote access. These attacks are often detected using intrusion detection methodologies, although these systems' effectiveness and accuracy are subpar. This paper proposes a new voting classifier composed of an ensemble of machine learning models trained and optimized using metaheuristic optimization. The employed metaheuristic optimizer is a new version of the whale optimization algorithm (WOA), which is guided by the dipper throated optimizer (DTO) to improve the exploration process of the traditional WOA optimizer. The proposed voting classifier categorizes the network intrusions robustly and efficiently. To assess the proposed approach, a dataset created from IoT devices is employed to record the efficiency of the proposed algorithm for binary attack categorization. The dataset records are balanced using the locality-sensitive hashing (LSH) and Synthetic Minority Oversampling Technique (SMOTE). The evaluation of the achieved results is performed in terms of statistical analysis and visual plots to prove the proposed approach's effectiveness, stability, and significance. The achieved results confirmed the superiority of the proposed algorithm for the task of network intrusion detection.

show abstract

Network Intrusion Detection Leveraging Machine Learning and Feature Selection

Cited by 19 publications

References 15 publications

Obfuscated Malware Memory Detection Employing Lazy Instance Based Learner Algorithm Based On Manhattan Distance Function

Obfuscated Malware Memory Detection Employing Lazy Instance Based Learner Algorithm Based On Manhattan Distance Function

A Machine Learning Method for Classification of Cervical Cancer

Voting Classifier and Metaheuristic Optimization for Network Intrusion燚etection

Contact Info

Product

Resources

About