An Analysis of Cross-Site-Scripting Attack with Accuracy using Support Vector Machine and Convolutional Neural Network

On the other hand, in contrast to the Convolutional Neural Network (CNN), the primary objective of this research project is to develop an efficient method for recognising Cross-Site Scripting assaults. The support vector machine, often known as SVM, will be used to achieve this goal. There are two different groups that have been used for the purpose of implementation in this article. A support vector machine is included inside Group 1, whereas a convolutional neural network is contained within Group 2. The size of the samples was determined by using Clincalc software with a GPower pretest of eighty percent, a threshold of five percent, and a confidence interval of ninety-five percent. The number of samples for each group is twenty, and the size of the samples was determined by using Clincalc. To put this into perspective, the accuracy of the Convolutional Neural Network is just 87%, but the accuracy of the Novel Support Vector Machine is 94%. In accordance with the results of the independent t test, the difference in significance between the groups is 0.001 (p0.05), which shows that the difference is statistically significant. When compared to convolutional neural networks (CNN), which generated lower accuracy rates, convolutional neural networks that include innovative support vector machines (SVM) yield greater accuracy rates.