Software Vulnerability Detection: A Comparison of Statistical and Machine Learning Algorithms

Software vulnerabilities can be defined as potential threats to an existing software structure. With the advent of networks and the internet to far and wide places, the software has become vulnerable to attacks by elements irrespective of their geographical locations. It would need consistent efforts and constant upgradation of vulnerability detection methods to keep up with the attacks. Machine learning methods can be used to detect vulnerabilities in less time. The proposed work’s main aim is to find the best possible methods to improve vulnerability detection. Classical statistical methods as well as hyper-tuned machine learning methods have been used to analyze vulnerability detection. The proposed work has employed the grid search method to improve the accuracy of SVM and neural networks. This study aims to move toward machine learning methods of vulnerability detection from classical statistical techniques with the help of empirical results, charts and graphs.