Security Enrichment in Intrusion Detection System Using Classifier Ensemble

Salunkhe, Uma R.; Mali, Suresh N.

doi:10.1155/2017/1794849

Cited by 18 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The subset of codes clustering with CHGL helps to detect profiles of high concept levels to find more attacks. In [4]proposed a hybrid IDS using ensemble classifier. They worked on data and its feature to improve the detection rate of the overall system.…”

Section: A Cascading Layered Approach For Intrusion Detection To Improve Detection Accuracy Of Major and Minor Attacksmentioning

confidence: 99%

A cascading layered approach for Intrusion Detection to improve detection accuracy of Major and Minor Attacks

2020

IJATCSE

View full text Add to dashboard Cite

The growth of computer network for inter communication and data sharing has also raised the challenge of security of data over network. There are many threat or attacks in network that tries to privacy theft of data over network. Intrusion Detection System (IDS) is helpful to protect network form attacks. The attacks over network is divided into four categories i.e. User-to-Root (U2R), Root-to-User (R2L), Prob and Denial-of-Service (DoS). In this paper, a cascading layered based approach is follow to make an IDS. The approach is followed to improve the detection rate of all categories of attacks. Feature selection for Prob & DoS attacks and U2R & R2L attacks is done. An Artificial Neural Network (ANN) is used to improve the detection accuracy of U2R and R2L attacks. The training data for minor attacks is resampled to detect any novel attacks. The proposed approach gives a very good results.

show abstract

Section: A Cascading Layered Approach For Intrusion Detection To Improve Detection Accuracy Of Major and Minor Attacksmentioning

confidence: 99%

A cascading layered approach for Intrusion Detection to improve detection accuracy of Major and Minor Attacks

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…In this work, Gamma and the fitting constant value for the Radial Basis function are also optimized, to get the good classification results. Researchers have also used an ensemble of different classifiers in order to increase the accuracy of system [6]. In [7], authors proposed three different strategies to extract relevant features.…”

Section: Related Workmentioning

confidence: 99%

“…So the selection of a proper subset of features which are highly relevant for the given task as well as uncorrelated to each other is desired [2]. IDS developed in [3,4,5,6,7,8,9,10] used different feature deduction methods for selecting relevant features, whereas IDS presented in [11,12,13,14,15,16] used evolution theory to detect good subset of features and achieve good accuracy. Some researchers also used deep learning based techniques for designing IDS [17,18,19,20,21,22].…”

Section: Introductionmentioning

confidence: 99%

Building an Effective Intrusion Detection System using Unsupervised Feature Selection in Multi-objective Optimization Framework

Suman,

Tripathy,

Saha

2019

Preprint

View full text Add to dashboard Cite

Intrusion Detection Systems (IDS) are developed to protect the network by detecting the attack. The current paper proposes an unsupervised feature selection technique for analyzing the network data. The search capability of the non-dominated sorting genetic algorithm (NSGA-II) has been employed for optimizing three different objective functions utilizing different information theoretic measures including mutual information, standard deviation, and information gain to identify mutually exclusive and a high variant subset of features. Finally, the Pareto optimal front of the different optimal feature subsets are obtained and these feature subsets are utilized for developing classification systems using different popular machine learning models like support vector machines, decision trees and k-nearest neighbour (k=5) classifier etc. We have evaluated the results of the algorithm on KDD-99, NSL-KDD and Kyoto 2006+ datasets. The experimental results on KDD-99 dataset show that decision tree provides better results than other available classifiers. The proposed system obtains the best results of 99.78% accuracy, 99.27% detection rate and false alarm rate of 0.2%, which are better than all the previous results for KDD dataset. We achieved an accuracy of 99.83% for 20% testing data of NSL-KDD dataset and 99.65% accuracy for 10-fold cross-validation on Kyoto dataset. The most attractive characteristic of the proposed scheme is that during the selection of appropriate feature subset, no labeled information is utilized and different feature quality measures are optimized simultaneously using the multi-objective optimization framework.

show abstract

“…On the other hand, advanced statistical methods, such as supervised and unsupervised machine learning (ML) systems that have been widely deployed for various detection tasks do not have this disadvantage [ 20 , 21 , 22 , 23 , 24 , 25 , 26 ]. It is important to note that the objective of a detection system is to detect specific categories of activity while keeping false-positive (FP) and false-negative (FN) numbers low.…”

Section: Introductionmentioning

confidence: 99%

Towards a Multi-Layered Phishing Detection

Rendall

Nisioti

Mylonas

2020

Sensors

View full text Add to dashboard Cite

Phishing is one of the most common threats that users face while browsing the web. In the current threat landscape, a targeted phishing attack (i.e., spear phishing) often constitutes the first action of a threat actor during an intrusion campaign. To tackle this threat, many data-driven approaches have been proposed, which mostly rely on the use of supervised machine learning under a single-layer approach. However, such approaches are resource-demanding and, thus, their deployment in production environments is infeasible. Moreover, most previous works utilise a feature set that can be easily tampered with by adversaries. In this paper, we investigate the use of a multi-layered detection framework in which a potential phishing domain is classified multiple times by models using different feature sets. In our work, an additional classification takes place only when the initial one scores below a predefined confidence level, which is set by the system owner. We demonstrate our approach by implementing a two-layered detection system, which uses supervised machine learning to identify phishing attacks. We evaluate our system with a dataset consisting of active phishing attacks and find that its performance is comparable to the state of the art.

show abstract

Security Enrichment in Intrusion Detection System Using Classifier Ensemble

Cited by 18 publications

References 11 publications

A cascading layered approach for Intrusion Detection to improve detection accuracy of Major and Minor Attacks

A cascading layered approach for Intrusion Detection to improve detection accuracy of Major and Minor Attacks

Building an Effective Intrusion Detection System using Unsupervised Feature Selection in Multi-objective Optimization Framework

Towards a Multi-Layered Phishing Detection

Contact Info

Product

Resources

About