Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/307990
Title: Hybrid Intrusion Detection Methods to Mitigate Denial of Service Attacks for Malicious Traffic Identification using Combined Machine Learning And Optimization Methods
Researcher: Lekha J
Guide(s): Padmavathi G
Keywords: Engineering and Technology
Computer Science
Computer Science Interdisciplinary Applications
University: Avinashilingam Deemed University For Women
Completed Date: 2018
Abstract: Due to the rapid developments in Internet, the network traffic has also increased permanently. newlineThe malicious traffic flow increases day by day in the network apart from non-malicious traffic flow. newlineThe malicious traffic flow may be due to cyber attacks and one of the challenging groups of cyber newlineattacks are Denial of Service Attacks. There are many challenges that must be understood in order to newlinedesign solutions to address the malicious traffic flow in DoS attacks. The fundamental challenge is newlinebased on two exploited weakness such as: i) the computer and network is flooded with more requests newlinethan it can handle at a time which leads to crash and ii) using vulnerabilities to malfunction an newlineapplication, host or a network. The exploited weakness occur due to the malicious traffic execution newlineflows, packet flow, network connection flows, transport layer segments and connection requests or newlineapplication service request messages. newlineMalicious traffic flow caused by DoS attacks makes unavailability of network resources thus newlineresulting in heavy financial loss to government and private organizations. An Intrusion Detection newlineSystem (IDS) is needed that aims at detecting malicious traffic flow caused by DoS attacks. Among newlineseveral intrusion detection approaches, the core approaches for detecting DoS attacks are Anomaly newlinedetection and Misuse detection approaches. Signature (Misuse) based detection approach is used to newlinedetect the known attacks from the traffic. Anomaly based detection approaches are efficient in newlineidentifying unknown attacks. Many researchers proposed Misuse, Anomaly and Hybrid intrusion newlinedetection models based on various detection methods such as Statistical based, Knowledge based, Soft newlineComputing and Machine Learning based methods. Even though the existing models provide newlineimproved results, certain research gaps have been observed. newlineThe primary objective of the research work is to device a defense mechanism for detecting newlinemalicious traffic flow in a network caused by vulnerability and flooding based exploited
Pagination: 223 p.
URI: http://hdl.handle.net/10603/307990
Appears in Departments:Department of Computer Science

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File114.43 kBAdobe PDFView/Open
02_certificate.pdf1.63 MBAdobe PDFView/Open
03_acknowledgement.pdf129.6 kBAdobe PDFView/Open
04_contents.pdf133.43 kBAdobe PDFView/Open
05_list of tables, figures, abbreviation.pdf143.18 kBAdobe PDFView/Open
06_chapter1.pdf427.52 kBAdobe PDFView/Open
07_chapter2.pdf347.11 kBAdobe PDFView/Open
08_chapter3.pdf244.14 kBAdobe PDFView/Open
09_chapter4.pdf767.08 kBAdobe PDFView/Open
10_chapter5.pdf1.33 MBAdobe PDFView/Open
11_chapter6.pdf1.13 MBAdobe PDFView/Open
12_chapter7.pdf1.08 MBAdobe PDFView/Open
13_chapter8.pdf121.24 kBAdobe PDFView/Open
14_annexures.pdf250.15 kBAdobe PDFView/Open
15_references.pdf185.13 kBAdobe PDFView/Open
80_recommendation.pdf121.24 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetric Badge: