scholarly journals A novel approach for selective feature mechanism for two-phase intrusion detection system

2019 ◽  
Vol 14 (1) ◽  
pp. 101
Author(s):  
B Narendra Kumar ◽  
M S V Sivarama Bhadri Raju ◽  
B Vishnu Vardhan
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Performance Metrics ◽  
Detection System ◽  
Computational Time ◽  
Support Vector ◽  
Phase System ◽  
Second Phase ◽  
Two Phase ◽  
Linear Dependency

Intrusion Detection is an important aspect to secure the computing systems from different intrusions. To improve the accuracy and to reduce the computational time, this paper proposes a two-phase hybrid method based on the SVM and RNN. In addition, this paper also had a proposal to obtain a few sets of features with a feature selection technique in which the detection performance increases. For the two-phase system, two different feature selection techniques were proposed which solves both the linear dependency and non-linear dependency between the features. In the first phase, the RNN combines with the proposed Joint Mutual Information Maximization (JMIM) based feature selection and in the second phase, the Support Vector Machine (SVM) combines with correlation based feature selection. Extensive simulations are carried out over the proposed system using two different datasets, NSL-KDD and Kyoto2006+. The performance is measured through the performance metrics such as Detection Rate (DR), Precision, False Alarm Rate (FAR), Accuracy and F-Score. Furthermore, a comparative analysis with few recent hybrid frameworks is also enumerated. The obtained results signify the effectiveness of proposed method.

scholarly journals Scrutinizing Attacks and Evaluating Performance Appraisal Parameters via Feature Selection in Intrusion Detection System

2021 ◽  
Author(s):  
Navroop Kaur ◽  
Meenakshi Bansal ◽  
Sukhwinder Singh S
Keyword(s):  
Feature Selection ◽  
Performance Evaluation ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Denial Of Service ◽  
Cyber Attacks ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Evaluation Parameters

Abstract In modern times the firewall and antivirus packages are not good enough to protect the organization from numerous cyber attacks. Computer IDS (Intrusion Detection System) is a crucial aspect that contributes to the success of an organization. IDS is a software application responsible for scanning organization networks for suspicious activities and policy rupturing. IDS ensures the secure and reliable functioning of the network within an organization. IDS underwent huge transformations since its origin to cope up with the advancing computer crimes. The primary motive of IDS has been to augment the competence of detecting the attacks without endangering the performance of the network. The research paper elaborates on different types and different functions performed by the IDS. The NSL KDD dataset has been considered for training and testing. The seven prominent classifiers LR (Logistic Regression), NB (Naïve Bayes), DT (Decision Tree), AB (AdaBoost), RF (Random Forest), kNN (k Nearest Neighbor), and SVM (Support Vector Machine) have been studied along with their pros and cons and the feature selection have been imposed to enhance the reading of performance evaluation parameters (Accuracy, Precision, Recall, and F1Score). The paper elaborates a detailed flowchart and algorithm depicting the procedure to perform feature selection using XGB (Extreme Gradient Booster) for four categories of attacks: DoS (Denial of Service), Probe, R2L (Remote to Local Attack), and U2R (User to Root Attack). The selected features have been ranked as per their occurrence. The implementation have been conducted at five different ratios of 60-40%, 70-30%, 90-10%, 50-50%, and 80-20%. Different classifiers scored best for different performance evaluation parameters at different ratios. NB scored with the best Accuracy and Recall values. DT and RF consistently performed with high accuracy. NB, SVM, and kNN achieved good F1Score.

scholarly journals A Novel Intrusion Detection System for RPL Based IoT Networks with Bio-Inspired Feature Selection and Ensemble Classifier

2021 ◽  
Author(s):  
Jayaprakash Pokala ◽  
B. Lalitha
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Ensemble Classifier ◽  
Support Vector ◽  
Routing Attacks ◽  
Salp Swarm Algorithm ◽  
Network Intrusion ◽  
Swarm Algorithm

Abstract Internet of Things (IoT) is the powerful latest trend that allows communications and networking of many sources over the internet. Routing protocol for low power and lossy networks (RPL) based IoT networks may be exposed to many routing attacks due to resource-constrained and open nature of the IoT nodes. Hence, there is a need for network intrusion detection system (NIDS) to protect RPL based IoT networks from routing attacks. The existing techniques for anomaly-based NIDS (ANIDS) subjects to high false alarm rate (FAR). Therefore, a novel bio-inspired voting ensemble classifier with feature selection technique is proposed in this paper to improve the performance of ANIDS for RPL based IoT networks. The proposed voting ensemble classifier combines the results of various base classifiers such as logistic Regression, support vector machine, decision tree, bidirectional long short-term memory and K-nearest neighbor to detect the attacks accurately based on majority voting rule. The optimized weights of base classifiers are obtained by using the feature selection method called simulated annealing based improved salp swarm algorithm (SA-ISSA), which is the hybridization of particle swarm optimization, opposition based learning and salp swarm algorithm. The experiments are performed with RPL-NIDDS17 dataset that contains seven types of attack instances. The performance of the proposed model is evaluated and compared with existing feature selection and classification techniques in terms of accuracy, attack detection rate (ADR), FAR and so on. The proposed ensemble classifier shows better performance with higher accuracy (96.4%), ADR (97.7%) and reduced FAR (3.6%).

scholarly journals An ensemble feature selection approach using hybrid kernel based SVM for network intrusion detection system

2021 ◽  
Vol 23 (1) ◽  
pp. 558
Author(s):  
Gaddam Venu Gopal ◽  
Gatram Rama Mohan Babu
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Network Intrusion Detection ◽  
Support Vector ◽  
Feature Subset ◽  
Network Intrusion ◽  
Feature Selection Approach ◽  
Hybrid Kernel

Feature selection is a process of identifying relevant feature subset that leads to the machine learning algorithm in a well-defined manner. In this paper, anovel ensemble feature selection approach that comprises of Relief  Attribute Evaluation and hybrid kernel-based support vector machine (HK-SVM) approach is proposed as a feature selection method for network intrusion detection system (NIDS). A Hybrid approach along with the combination of Gaussian and Polynomial methods is used as a kernel for support vector machine (SVM). The key issue is to select a feature subset that yields good accuracy at a minimal computational cost. The proposed approach is implemented and compared with classical SVM and simple kernel. Kyoto2006+, a bench mark intrusion detection dataset,is used for experimental evaluation and then observations are drawn.

A Comparative Study on the Feature Selection Techniques for Intrusion Detection System

2019 ◽  
Vol 8 (1) ◽  
pp. 42-47
Author(s):  
D. Selvamani ◽  
V. Selvi
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Comparative Study ◽  
Intrusion Detection System ◽  
Detection System ◽  
Feature Selection Method ◽  
Support Vector ◽  
Network Intrusion ◽  
Chi Square Analysis ◽  
Feature Selection Techniques

The Intrusion Detection System (IDS) can be used broadly for securing the network. Intrusion detection systems (IDS) are typically positioned laterally through former protecting safety automation, like access control and verification, as a subsequent line of resistance that guards data classifications. Feature selection is employed to diminish the number of features in various applications where data has more than hundreds of attributes. Essential or relevant attribute recognition has converted a vital job to utilize data mining algorithms efficiently in today world situations. This article describes the comparative study on the Information Gain, Gain Ratio, Symmetrical Uncertainty, Chi-Square analysis feature selection techniques with different Classification methods like Artificial Neural Network, Naïve Bayes and Support Vector Machine. In this article, different performance metrics has utilized to choose the appropriate Feature Selection method for better data classification in IDS.

scholarly journals Towards Improved Random Forest based Feature Selection for Intrusion Detection in Smart IOT Environment

2019 ◽  
Vol 8 (11) ◽  
pp. 749-757
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Intrusion Detection ◽  
Performance Metrics ◽  
Detection System ◽  
Denial Of Service ◽  
Learning Approaches ◽  
Iot Devices ◽  
Sensitivity Specificity ◽  
Research Challenge

Internet of Things (IoT) is raised as most adaptive technologies for the end users in past few years. Indeed of being popular, security in IoT turned out to be a crucial research challenge and a sensible topic which is discussed very often. Denial of Service (DoS) attack is encountered in IoT sensor networks by perpetrators with numerous compromised nodes to flood certain targeted IoT device and thus resulting in vulnerability or service unavailability. Features that are encountered from the malicious node can be utilized effectually to recognize recurring patterns or attack signature of network based or host based attacks. Henceforth, feature extraction using machine learning approaches for modelling of Intrusion detection system (IDS) have been cast off for identification of threats in IoT devices. In this investigation, Kaggle dataset is measured as benchmark dataset for detecting intrusion is considered initially. These dataset includes 41 essential attributes for intrusion identification. Next, selection of features for classifiers is done with an improved Weighted Random Forest Information extraction (IW-RFI). This proposed WRFI approach evaluates the mutual information amongst the attributes of features and select the optimal features for further computation. This work primarily concentrates on feature selection as effectual feature selection leads to effectual classification. Finally, performance metrics like accuracy, sensitivity, specificity is computed for determining enhanced feature selection. The anticipated model is simulated in MATLAB environment, which outperforms than the existing approaches. This model shows better trade off in contrary to prevailing approaches in terms of accurate detection of threats in IoT devices and offers better transmission over those networks.

scholarly journals Classification model for accuracy and intrusion detection using machine learning approach

2021 ◽  
Vol 7 ◽  
pp. e437
Author(s):  
Arushi Agarwal ◽  
Purushottam Sharma ◽  
Mohammed Alshehri ◽  
Ahmed A. Mohamed ◽  
Osama Alfarraj
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Nearest Neighbor ◽  
Performance Metrics ◽  
Detection System ◽  
Confusion Matrix ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Support Vector ◽  
K Nearest Neighbor

In today’s cyber world, the demand for the internet is increasing day by day, increasing the concern of network security. The aim of an Intrusion Detection System (IDS) is to provide approaches against many fast-growing network attacks (e.g., DDoS attack, Ransomware attack, Botnet attack, etc.), as it blocks the harmful activities occurring in the network system. In this work, three different classification machine learning algorithms—Naïve Bayes (NB), Support Vector Machine (SVM), and K-nearest neighbor (KNN)—were used to detect the accuracy and reducing the processing time of an algorithm on the UNSW-NB15 dataset and to find the best-suited algorithm which can efficiently learn the pattern of the suspicious network activities. The data gathered from the feature set comparison was then applied as input to IDS as data feeds to train the system for future intrusion behavior prediction and analysis using the best-fit algorithm chosen from the above three algorithms based on the performance metrics found. Also, the classification reports (Precision, Recall, and F1-score) and confusion matrix were generated and compared to finalize the support-validation status found throughout the testing phase of the model used in this approach.

Building an Effective Approach toward Intrusion Detection Using Ensemble Feature Selection

2019 ◽  
Vol 13 (3) ◽  
pp. 31-47 ◽  
Author(s):  
Alok Kumar Shukla ◽  
Pradeep Singh
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Detection System ◽  
Classification Performance ◽  
Support Vector ◽  
Web Traffic ◽  
Data Set ◽  
Optimal Subset ◽  
Benchmark Datasets ◽  
Kdd Cup 99

The duplicate and insignificant features present in the data set to cause a long-term problem in the classification of network or web traffic. The insignificant features not only decrease the classification performance but also prevent a classifier from making accurate decisions, exclusively when substantial volumes of data are managed. In this article, the author introduced an ensemble feature selection (EFS) technique, where multiple homogeneous feature selection (FS) methods are combined to choose the optimal subset of relevant and non-redundant features. An intrusion detection system, named support vector machine-based IDS (SVM-IDS), is prompted using the feature selected by the proposed method. The SVM-IDS performance is evaluated using two benchmark datasets of intrusion detection, including KDD Cup 99 and NSL-KDD. Our proposed method provided more significant features for SVM-IDS and compared with the other state-of-the-art methods. The experimental results demonstrate that proposed method achieves a maximum accuracy as 98.95% in KDD Cup 99 data set and 98.12% in the NSL-KDD data set.

Intrusion Detection System Based on Hybrid Feature Selection and Support Vector Machine (HFS-SVM)

2015 ◽  
Vol 781 ◽  
pp. 125-128 ◽  
Author(s):  
Yonchanok Khaokaew ◽  
Tanapat Anusas-Amornkul ◽  
Koonlachat Meesublak
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Intrusion Detection ◽  
Motif Discovery ◽  
Detection System ◽  
Random Projection ◽  
Support Vector ◽  
Training Time ◽  
Detection Techniques ◽  
Projection Techniques

In recent years, anomaly based intrusion detection techniques are continuously developed and a support vector machine (SVM) is one of the technique. However, it requires training time and storage if there are lots of numbers of features. In this paper, a hybrid feature selection, using Correlation based on Feature Selection and Motif Discovery using Random Projection techniques, is proposed to reduce the number of features from 41 to 3 features with KDD'99 dataset. It is compared with a regular SVM technique with 41 features. The results show that the accuracy rate is also high at 98% and the training time is less than the regular SVM almost by half.

Sign in / Sign up

Export Citation Format

Share Document