Intrusion detection using data mining techniques

Ektefa, Mohammadreza; Memar, Sara; Sidi, Fatimah; Affendey, Lilly Suriani

doi:10.1109/infrkm.2010.5466919

Cited by 102 publications

(42 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weight is determined where the minimum depth of the decision tree at which each feature is checked inside the tree and the weights of features that do not appear in the decision tree are allocated a value of zero. Ektefa et al [19], used different data mining method for intrusion detection and they found that the decision tree classifier was performing better than the SVM learning algorithm.…”

Section: Description Of Nsl-kddmentioning

confidence: 99%

A Subset Feature Elimination Mechanism for Intrusion Detection System

Nkiama¹,

Said²,

Saidu³

2016

ijacsa

View full text Add to dashboard Cite

Abstract-several studies have suggested that by selecting relevant features for intrusion detection system, it is possible to considerably improve the detection accuracy and performance of the detection engine. Nowadays with the emergence of new technologies such as Cloud Computing or Big Data, large amount of network traffic are generated and the intrusion detection system must dynamically collected and analyzed the data produce by the incoming traffic. However in a large dataset not all features contribute to represent the traffic, therefore reducing and selecting a number of adequate features may improve the speed and accuracy of the intrusion detection system. In this study, a feature selection mechanism has been proposed which aims to eliminate non-relevant features as well as identify the features which will contribute to improve the detection rate, based on the score each features have established during the selection process. To achieve that objective, a recursive feature elimination process was employed and associated with a decision tree based classifier and later on, the suitable relevant features were identified. This approach was applied on the NSL-KDD dataset which is an improved version of the previous KDD 1999 Dataset, scikit-learn that is a machine learning library written in python was used in this paper. Using this approach, relevant features were identified inside the dataset and the accuracy rate was improved. These results lend to support the idea that features selection improve significantly the classifier performance. Understanding the factors that help identify relevant features will allow the design of a better intrusion detection system.

show abstract

Section: Description Of Nsl-kddmentioning

confidence: 99%

A Subset Feature Elimination Mechanism for Intrusion Detection System

Nkiama¹,

Said²,

Saidu³

2016

ijacsa

View full text Add to dashboard Cite

show abstract

“…The entire KDD Cup "99 data set contains 41 features. Connections are labeled as normal or attacks fall into 4 main categories [13].…”

Section: Data Collection and Preprocessingmentioning

confidence: 99%

An Competent Intrusion Detection System using Relevance Vector Machine

Jaiganesh¹,

Sumathi²

2013

IJCA

View full text Add to dashboard Cite

Nowadays everyone needs Internet for their useful. So internet becomes a public network in the world wide. Intrusion Detection (ID) is the art of detecting inappropriate, incorrect, or anomalous activity. It is a security service that monitors and analyzes system events for the idea of finding, and providing near real-time or realtime notice of, attempts in order to access system resources in an unauthorized manner In proposed system the `relevance vector machine' (RVM), a model of same functional form to the popular and state-of-the-art `support vector machine' (SVM). It demonstrate that by exploiting a probabilistic Bayesian learning framework and it can derive accurate prediction models which typically utilize dramatically fewer basis functions than a comparable SVM. These include the benefits of probabilistic predictions, automatic estimation of `nuisance' parameters and the facility to utilize arbitrary basis functions. The experiment is carried out with the help of MATLAB and WEKA by using KDD Cup 1999 dataset and the results indicate that the proposed technique can achieve higher detection rate and very low false alarm rate than the regular SVM algorithms.

show abstract

“…In contrast to statistical techniques, machine learning techniques are well suited to learning patterns with no apriori knowledge of what those patterns may be. Clustering and Classification are probably the two most popular machine learning problems [29], [7].…”

Section: Related Workmentioning

confidence: 99%

“…either normal or malicious. The challenge in this method is to minimize the number of false positives and false negatives [7]. Five general categories of techniques have been tried to perform classification for intrusion detection purposes [9]: a) Inductive Rule Generation: The RIPPER (rule learning program) System is the most popular representative of classification techniques.…”

Section: Related Workmentioning

confidence: 99%

Design of Intrusion Detection System using Fuzzy Class-Association Rule Mining based on Genetic Algorithm

Dhopte¹,

Tarapore²

2012

IJCA

View full text Add to dashboard Cite

Now security is considered as a major issue in networks, since the network has extended dramatically. Therefore, intrusion detection systems have attracted attention, as it has an ability to detect intrusion accesses effectively. These systems identify attacks and react by generating alerts or by blocking the unwanted data/traffic. The proposed system includes fuzzy logic with a data mining method which is a class-association rule mining method based on genetic algorithm. Due to the use of fuzzy logic, the proposed system can deal with mixed type of attributes and also avoid the sharp boundary problem. Genetic algorithm is used to extract many rules which are required for anomaly detection systems. An association-rulemining method is used to extract a sufficient number of important rules for the user's purpose rather than to extract all the rules meeting the criteria which are useful for misuse detection. Experimental results with KDD99 Cup database from MIT Lincoln Laboratory show that the proposed method provides competitively high detection rates compared with crisp data mining.

show abstract

Intrusion detection using data mining techniques

Cited by 102 publications

References 4 publications

A Subset Feature Elimination Mechanism for Intrusion Detection System

A Subset Feature Elimination Mechanism for Intrusion Detection System

An Competent Intrusion Detection System using Relevance Vector Machine

Design of Intrusion Detection System using Fuzzy Class-Association Rule Mining based on Genetic Algorithm

Contact Info

Product

Resources

About