scholarly journals A Comparative Study of Data Mining Algorithms for High Detection Rate in Intrusion Detection System

2018 ◽  
Vol 2 (1) ◽  
pp. 49-57 ◽  
Author(s):  
Nabeela Ashraf ◽  
Waqar Ahmad ◽  
Rehan Ashraf
Keyword(s):  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection Rate ◽  
Detection System ◽  
Huge Amount ◽  
High Detection Rate ◽  
Data Mining Algorithms ◽  
Secure Networks ◽  
Mining Algorithms ◽  
Speed And Accuracy

Due to the fast growth and tradition of the internet over the last decades, the network security problems are increasing vigorously. Humans can not handle the speed of processes and the huge amount of data required to handle network anomalies. Therefore, it needs substantial automation in both speed and accuracy. Intrusion Detection System is one of the approaches to recognize illegal access and rare attacks to secure networks. In this proposed paper, Naive Bayes, J48 and Random Forest classifiers are compared to compute the detection rate and accuracy of IDS. For experiments, the KDD_NSL dataset is used.

scholarly journals A feature selection algorithm combining information gain and multi-objective genetic search for intrusion detection system

2021 ◽  
Vol 336 ◽  
pp. 08008
Author(s):  
Tao Xie
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection Rate ◽  
Information Gain ◽  
Detection System ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Genetic Search ◽  
Multi Objective

In order to improve the detection rate and speed of intrusion detection system, this paper proposes a feature selection algorithm. The algorithm uses information gain to rank the features in descending order, and then uses a multi-objective genetic algorithm to gradually search the ranking features to find the optimal feature combination. We classified the Kddcup98 dataset into five classes, DOS, PROBE, R2L, and U2R, and conducted numerous experiments on each class. Experimental results show that for each class of attack, the proposed algorithm can not only speed up the feature selection, but also significantly improve the detection rate of the algorithm.

An Intelligent Network Intrusion Detection System Based on Multi-Modal Support Vector Machines

2013 ◽  
Vol 7 (4) ◽  
pp. 37-52
Author(s):  
Srinivasa K G
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Intelligent Network ◽  
Statistical Machine Learning ◽  
High Detection Rate ◽  
Network Intrusion

Increase in the number of network based transactions for both personal and professional use has made network security gain a significant and indispensable status. The possible attacks that an Intrusion Detection System (IDS) has to tackle can be of an existing type or of an entirely new type. The challenge for researchers is to develop an intelligent IDS which can detect new attacks as efficiently as they detect known ones. Intrusion Detection Systems are rendered intelligent by employing machine learning techniques. In this paper we present a statistical machine learning approach to the IDS using the Support Vector Machine (SVM). Unike conventional SVMs this paper describes a milti model approach which makes use of an extra layer over the existing SVM. The network traffic is modeled into connections based on protocols at various network layers. These connection statistics are given as input to SVM which in turn plots each input vector. The new attacks are identified by plotting them with respect to the trained system. The experimental results demonstrate the lower execution time of the proposed system with high detection rate and low false positive number. The 1999 DARPA IDS dataset is used as the evaluation dataset for both training and testing. The proposed system, SVM NIDS is bench marked with SNORT (Roesch, M. 1999), an open source IDS.

scholarly journals Security Enrichment in Intrusion Detection System Using Classifier Ensemble

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Uma R. Salunkhe ◽  
Suresh N. Mali
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection Rate ◽  
Detection System ◽  
Hybrid Approach ◽  
Classifier Ensemble ◽  
Intrusion Detection Systems ◽  
Detection Rates ◽  
Detection Systems

In the era of Internet and with increasing number of people as its end users, a large number of attack categories are introduced daily. Hence, effective detection of various attacks with the help of Intrusion Detection Systems is an emerging trend in research these days. Existing studies show effectiveness of machine learning approaches in handling Intrusion Detection Systems. In this work, we aim to enhance detection rate of Intrusion Detection System by using machine learning technique. We propose a novel classifier ensemble based IDS that is constructed using hybrid approach which combines data level and feature level approach. Classifier ensembles combine the opinions of different experts and improve the intrusion detection rate. Experimental results show the improved detection rates of our system compared to reference technique.

Weighted K Nearest Neighbour-Based Cooperation Intrusion Detection System for Wireless Sensor Networks

2012 ◽  
Vol 263-266 ◽  
pp. 2972-2978
Author(s):  
Ju Long Pan ◽  
Ling Long Hu ◽  
Wen Jin Li ◽  
Hui Cui ◽  
Zi Yin Li
Keyword(s):  
Wireless Sensor Networks ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection Rate ◽  
Detection System ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Nearest Neighbour ◽  
Malicious Nodes ◽  
Detection Scheme

To identify the malicious nodes timely in wireless sensor networks(WSNs), a cooperation intrusion detection scheme based on weighted k Nearest Neighbour(kNN) is proposed. Given a few types of sensor nodes, the test model extracts the properties of sensor nodes related with the known types of malicious nodes, and establishes sample spaces of all sensor nodes which participate in network activities. According to the known node’s attributes sampled, the unknown type sensor nodes are classified based on weighted kNN. Considering of energy consumption, an intrusion detection system selection algorithm is joined in the sink node. Simulation results show that the scheme has a lower false detection rate and a higher detection rate at the same time, and it can preserve energy of detection nodes compared with an existing intrusion detection scheme.

Sign in / Sign up

Export Citation Format

Share Document