Effective Forecasting for Enhancing the Precision in U2R Attacks in Wireless Networks Through the Use of New CNN Alexnet Compared to Support Vector Machine Algorithm

The primary objective of this work is to utilize DL (Deep Learning) models to enhance the accuracy of forecasting User-to-Root (U2R) attacks using intrusion dataset. The research data was sourced from the Github database system. A sample size of 22543 with 30 iterations was employed for predicting a User-to-Root (U2R) attack with 15 samples each from Group 1 and Group 2. achieved with a G-power of 0.8, alpha and beta values of 0.05 and 0.2, and a confidence interval of 95%. Both the Novel Convolutional Neural Network AlexNet (CNN AlexNet) and Support Vector Machine were utilized for U2R attack prediction using an equal number of data samples (N=15), The accuracy of the CNN AlexNet classifier was validated at 92.4060%, while that of SVM at 87.4387%. The distinction between these two accuracies is evident. The significant value was determined as p=0.525 (p>0.05) The developed Novel Convolutional Neural Network AlexNet model outperforms the SVM classifier in predicting U2R attacks from intrusion datasets, as evidenced by the outcome of this work