11464

10540

كارشناسي ارشد

هوش مصنوعي

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1395

دوازده، 79ص.: مصور

علي فانيان

مازيار پالهنگ، مهران صفاياني

1395/07/10

مهندسي برق و كامپيوتر

ID10540

A graph based online feature selection to improve detection of new attacks in intrusion detection systems Hajar Dastanpoor h dastanpoor@ec iut ac ir May 25 2016 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran Degree M Sc Language Farsi Supervisor Prof Ali Fanian a fanian@cc iut ac ir Abstract Today intrusion detection systems as one of the most important system are used in detecting attacks and upgradenetwork security Usually these systems are facing with large data sets and many features Hence choosing the appropriatefeatures can be suitable solution to improve their performance in detecting attacks On the other side the outbreak ofnew attacks on computer networks continual discovery of new vulnerabilities is an inevitable problem To deal with thisproblem intrusion detection systems not only should profit the acquired knowledge from the past but also adapt themselveswith the new condition which is different from the past to detect new attacks Using the online method to select suitablefeatures as new attacks are occurred can be appropriate solution to this end In this study in order to increase accuracyin detecting attacks we present a new graph based method for online feature selection In general the proposed methodwith the arrival of a limited number of samples flow of network packets initially irrelevant features are removed Thenin order to reduce the search space features are clustered based on graph theory At any stage after the arrival of newsamples new clusters include features are created who may different from pervious step Therefore to find the appropriateclusters clusters that properly classify features followed by appropriate features the two sets of clusters are combined It should be mentioned that the appropriate clusters saved to the composition of the new clusters In continuation fromappropriate clusters the number of relevant features with minimum redundancy is selected Mentioned process is repeatedwith the new arrival samples The evaluation results indicate that the proposed method compared to other similar onlinefeature selection methods has better performance In other words by selecting the appropriate features lead to increase theaccuracy of classification of the samples In addition the proposed method has less run time and is also faster compared tooffline methods and lead to acceptable of the accurate in classify the samples Key Words Online feature selection clustering ensemble clustering intrusion detection system

علي فانيان

مازيار پالهنگ، مهران صفاياني