Journal ArticleDOI
An enhanced J48 classification algorithm for the anomaly intrusion detection systems
Reads0
Chats0
TLDR
This enhanced J48 algorithm is seen to help in an effective detection of probable attacks which could jeopardise the network confidentiality and showed a better, accurate and more efficient performance without using the above-mentioned features when compared to the feature selection procedure.Abstract:
In this paper, we have developed an enhanced J48 algorithm, which uses the J48 algorithm for improving the detection accuracy and the performance of the novel IDS technique. This enhanced J48 algorithm is seen to help in an effective detection of probable attacks which could jeopardise the network confidentiality. For this purpose, the researchers used many datasets by integrating different approaches like the J48, Naive Bayes, Random Tree and the NB-Tree. An NSL KDD intrusion dataset was applied while carrying out all experiments. This dataset was divided into 2 datasets, i.e., training and testing, which was based on the data processing. Thereafter, a feature selection method based on the WEKA application was used for evaluating the efficacy of all the features. The results obtained suggest that this algorithm showed a better, accurate and more efficient performance without using the above-mentioned features when compared to the feature selection procedure. An implementation of this algorithm guaranteed the dataset classification based on a detection accuracy of 99.88% for all the features when using the 10-fold cross-validation test, a 90.01% accuracy for the supplied test set after using the complete test datasets along with all the features and a 76.23% accuracy for supplying the test set after using the test-21 dataset along with all features.read more
Citations
More filters
Journal ArticleDOI
CICIDS-2017 Dataset Feature Analysis With Information Gain for Anomaly Detection
Kurniabudi,Deris Stiawan,Darmawijoyo,Mohammad Yazid Bin Idris,Alwi M. Bamhdi,Rahmat Budiarto +5 more
TL;DR: The experiment results show that the number of relevant and significant features yielded by Information Gain affects significantly the improvement of detection accuracy and execution time.
Journal ArticleDOI
A taxonomy of network threats and the effect of current datasets on intrusion detection systems
Hanan Hindy,David Brosset,David Brosset,Ethan Bayne,Amar Seeam,Christos Tachtatzis,Robert Atkinson,Xavier Bellekens +7 more
TL;DR: In this paper, the authors provide researchers with two key pieces of information; a survey of prominent datasets, analyzing their use and impact on the development of the past decade's Intrusion Detection Systems (IDS) and a taxonomy of network threats and associated tools to carry out these attacks.
Journal ArticleDOI
A Feature Selection Model for Network Intrusion Detection System Based on PSO, GWO, FFA and GA Algorithms
TL;DR: It was found that the intrusion detection system with fewer features will increase accuracy and the proposed feature selection model for NIDS is rule-based pattern recognition to discover computer network attack which is in the scope of Symmetry journal.
Journal ArticleDOI
A new hybrid approach for intrusion detection using machine learning methods
TL;DR: It has been shown that the proposedIDS has high accuracy and a low false positive rates in all attack types.
References
More filters
Book
Data Mining: Concepts and Techniques
TL;DR: This book presents dozens of algorithms and implementation examples, all in pseudo-code and suitable for use in real-world, large-scale data mining projects, and provides a comprehensive, practical look at the concepts and techniques you need to get the most out of real business data.
Book
C4.5: Programs for Machine Learning
TL;DR: A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Journal Article
Data Mining Concepts and Techniques
TL;DR: Data mining is the search for new, valuable, and nontrivial information in large volumes of data, a cooperative effort of humans and computers that is possible to put data-mining activities into one of two categories: Predictive data mining, which produces the model of the system described by the given data set, or Descriptive data mining which produces new, nontrivials information based on the available data set.
Journal ArticleDOI
A Survey on Evolutionary Computation Approaches to Feature Selection
TL;DR: This paper presents a comprehensive survey of the state-of-the-art work on EC for feature selection, which identifies the contributions of these different algorithms.