Determining False Positive Analysis of Software Vulnerabilities with Predefined Scan Rules using Random Forest Classifier and Decision Tree Technique
Amilineni MahendraVardhan, S. Sridhar · 2022
The primary objective of this study is to develop a method that can accurately forecast novel software vulnerabilities in websites by favouring the Random Forest Classifier (RFC) technique over the Decision Tree Method (DT). With a pretest power of 80%, a threshold of 0.05%, and a confidence interval of 95%, the sample size is computed using the Gpower software and determined to be 10 per group. When it comes to forecasting software vulnerabilities, RFC has a much better accuracy of 97.80% than the DT method, which only has an accuracy of 85.95%. With a significance value of 0.034 (p0.05), the RFC method performs significantly better than the DT algorithm. The RFC method is superior to the DT algorithm in terms of its ability to predict software vulnerabilities.