Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/455452
Title: | Knowledge based Intrusion Detection System by deep Neural Network Learning |
Researcher: | Pandey, Rajkumar |
Guide(s): | Shrivastava, Shiv Shakti |
Keywords: | Artificial Neural Network Computer Science Computer Science Information Systems Engineering and Technology Intrusion Detection System Shuffled frog Leaping Vector Machine |
University: | Rabindranath Tagore University, Bhopal |
Completed Date: | 2021 |
Abstract: | The intrusion detection systems (IDSs) are essential elements when it comes to the newlineprotection of an ICT infrastructure. Intrusion detection systems (IDSs) are newlinewidespread systems able to passively or actively control intrusive activities in a newlinedefined host and network perimeter. Recently, different IDSs have been proposed by newlineintegrating various detection techniques, generic or adapted to a specific domain newlineand to the nature of attacks operating on. This work focus on the network intrusion newlinedetection using SVM and neural network. Here SVM classify network behavior into newlinetwo class first is safe and other is unsafe. newlineOnce unsafe network is identified then trained neural network identified attack type newlineof the input sessions. So Whole work is divide into two modules, first is separation of newlinesafe and unsafe session from the dataset using SVM. Then in second module newlineidentification of type of intrusion is done in unsafe network by EBPNN. newlineThis work has proposed SFLANN (Shuffled Frog Leaping and Artificial Neural newlineNetwork) have three modules first is selection of features from available set of newlinefeatures than second is training of neural network was performed from available set newlineof filtered features. Finally, in third module testing was performed on the trained newlineneural network. Here selection of features was done by Shuffled Frog Leaping newlineAlgorithm and training of Error Back Propagation Neural Network was performed. newlineHence objective of this paper was to reduce number of features with increase newlineintrusion detection accuracy. Experiment was done on real dataset NSL-KDD while newlinecomparison was done by existing methods. Results shows that proposed SVM and newlineEBPNN model has increase the precision while accuracy was enhance It was also newlineshows that proposed SFLANN model has increase the precision while accuracy was newlineenhance by 2.03%. newlineThis enhancement was achieved by use of SFLANN for initial feature selection model. newlineAs this selection of features is done by genetic algorithm, so neural network learning newlinewas get improved. Comparison of |
Pagination: | xii,101.pages |
URI: | http://hdl.handle.net/10603/455452 |
Appears in Departments: | Department of Computer Science Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 466.47 kB | Adobe PDF | View/Open |
02_ preliminary pages.pdf | 391.57 kB | Adobe PDF | View/Open | |
03_ contents.pdf | 203.26 kB | Adobe PDF | View/Open | |
04_ abstract.pdf | 187.01 kB | Adobe PDF | View/Open | |
05_ chapter 1.pdf | 537.24 kB | Adobe PDF | View/Open | |
06_ chapter 2.pdf | 207.17 kB | Adobe PDF | View/Open | |
07_ chapter 3.pdf | 365.61 kB | Adobe PDF | View/Open | |
08_ chapter 4.pdf | 401.79 kB | Adobe PDF | View/Open | |
09_ chapter 5.pdf | 580.17 kB | Adobe PDF | View/Open | |
10 _chapter 6.pdf | 102.18 kB | Adobe PDF | View/Open | |
11_ annexures.pdf | 515.77 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 756 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: