International Journal of Scientific and Research Publications

Home
About Us
Editorial Board

Online Publication

Log In
New User?
       Register Now!
Forgot Password?
       Email Password!


Call For Papers

Call for Research Paper

Authors

Online Submission
Paper Submission Guidelines
Online Publication Charge
Print Publication Charge
How to publish research paper
Publication Certificate
Research Catalogue
Resources
FAQs

Reviewer

Join Reviewer Panel
Reviewer Guidelines

IJSRP Publications

E-Journal
Print Journal

Downloads

IJSRP Paper Format
Instructions

Contact Us

Feedback Form
Contact Us
Site Map

IJSRP, Volume 9, Issue 2, February 2019 Edition [ISSN 2250-3153]



      Roshan Pokhrel, Prabhat Pokharel, Arun Kumar Timalsina, PhD

Abstract: Intrusion Detection System (IDS) is a form of defense that aims to detect suspicious activities and attack against information systems in general. With new types of attacks appearing continuously, developing adaptive and flexible security oriented approaches is a severe challenge. In this scenario, this thesis presents an anomaly-based intrusion detection technique as a valuable technology to protect the target system against malicious activities. This technique uses a semi-supervised learning model to identify and learn from past events as manifested in system logs and build a user behavior profile. The observed behavior of the user is analyzed to infer whether or not the normal profile supports the observed one. This is carried out using two-class classifiers. A new hybrid approach using Support Vector Machine (SVM) and Naïve Bayes (NB) is proposed to provide better accuracy and to reduce the problem of high false positive. The comparison of the proposed approach is made with other SVM and NB techniques. Hybrid approach is found to outperform SVM and NB. For the validation of the result, cross-validation is employed, and the result is presented using Receiver Operating Characteristics (ROC) curve. The experimentation is implemented in datasets from two different organizations.

[Reference this Paper]   [BACK]

Ooops! It appears you don't have a PDF plugin for this barrPostingser. you can click here to download the PDF file.

Reference this Research Paper (copy & paste below code):

Roshan Pokhrel, Prabhat Pokharel, Arun Kumar Timalsina, PhD (2019); Anomaly-Based – Intrusion Detection System using User Profile Generated from System Logs; International Journal of Scientific and Research Publications (IJSRP) 9(2) (ISSN: 2250-3153), DOI: http://dx.doi.org/10.29322/IJSRP.9.02.2019.p8631

IJSRP PUBLICATIONS

Home

About Us
Editorial Board
Call for Paper

Call for Research Paper
Paper Status
IJSRP Paper Format
Join Us

Download e-journal
Join Forum
Invite Friends
Subscribe
Get Social with Us!



Copyright © 2011-2016, IJSRP Inc., All rights reserved.