Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/480115
Title: | Performance enhancement of Intrusion detection system using Hybridized algorithmic approach on Cloud environment |
Researcher: | Ranjithkumar, S |
Guide(s): | Chenthur Pandian |
Keywords: | Engineering and Technology Computer Science Computer Science Information Systems Intrusion detection system Hybridized algorithmic Cloud environment |
University: | Anna University |
Completed Date: | 2022 |
Abstract: | Due to the rapid expansion of the internet, safeguarding system newlineand communication capabilities continues to be an important problem and newlineworry for numerous businesses and academics, especially in the wake of newlineexpansion and new and technological advancement. In information security, newlinethe application and development of intrusion detection systems have become newlinehighly important. Cybersecurity is a critical network management tool in the newlinefight against destructive cyber assaults and unauthorized network newlineconnectivity. It has been a challenging topic for an Intrusion Detection newlineSystem (IDS) to properly distinguish known and a new assault with minimal newlineeducation information but number of incidents have been steadily increasing. newlineAs a result, three novel innovations derived from data extraction and pattern newlinerecognition approaches were incorporated in this research for reliably and newlineeffectively identifying both known and new threats with erroneous or newlineinadequate training material. newlineAccording to preliminary research, IDS were viewed as a newlinecritical component in meeting security needs. Various Machine Learning newline(ML) methodologies have recently been applied to simulate effective IDS. newlineThe majority of IDS were structured or unstructured and are reliant on newlinemachine learning techniques. An ID with supervised methods, on the other newlinehand, was based on labelled data. This is a widespread flaw that makes it newlineimpossible to detect assault sequences. Unsupervised learning, on the other newlinehand, does not produce adequate results. As a result, this report concentrated newlineon a semi-supervised teaching method for vulnerability scanning in cloud newlinesystems called as Fuzzy based moderately method using Latent Dirichlet newlineAllocation (F-LDA). newline |
Pagination: | xvii,148p. |
URI: | http://hdl.handle.net/10603/480115 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 10.21 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 1.05 MB | Adobe PDF | View/Open | |
03_content.pdf | 111.49 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 153.8 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 316.9 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 1.05 MB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 1.28 MB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 1.25 MB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 1.22 MB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 969.98 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 76.93 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: