Implementation of support vector machine with accuracy for detecting cross-site-scripting attack compared to K-nearest neighbors for web applications

The primary aim of this research is to create an effective approach for identifying Cross-Site Scripting (XSS) attacks by utilizing a novel Support Vector Machine (SVM) and contrasting it with the K-Nearest Neighbor (KNN) method. For this study, two distinct cohorts were utilized: group 1 represente...

Full description

Saved in:
Bibliographic Details
Main Authors: Nad, P. T., Kumari, V. S., Ramasenderan, N.
Format: Conference Proceeding
Language:English
Subjects:
Applications programs
Confidence intervals
Statistical analysis
Support vector machines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The primary aim of this research is to create an effective approach for identifying Cross-Site Scripting (XSS) attacks by utilizing a novel Support Vector Machine (SVM) and contrasting it with the K-Nearest Neighbor (KNN) method. For this study, two distinct cohorts were utilized: group 1 represented the integrated Support Vector Machine, meanwhile group 2 represented K-Nearest Neighbor approach. Each group consisted of 20 samples, determined through Clincalc software, incorporating a pretest power of 80 percent, a significance level of 5%, with a confidence level of 95%. In this study, the incorporated Support Vector Machine achieved a precision of 94%, whereas K-Nearest Neighbor method yielded an accuracy of 84%. The statistical analysis, utilizing an independent t-test (p
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0229213