Analyzing machine learning algorithms for antivirus applications: a study on decision trees, support vector machines, and neural networks

Abstract

Machine Learning (ML) methods and tools are reshaping the cybersecurity landscape, enhancing the overall preparedness of organizations to ensure the confidentiality, integrity, and availability of processes and data. In the realm of cybersecurity, independent response, and detection, AI tools are being used extensively. This study delves into the effectiveness of three prominent machine learning algorithms – decision trees, support vector machines, and neural networks – in enhancing antivirus decision and response capabilities. Our study, which includes an extensive literature review on using ML techniques in the cybersecurity incident response and detection domain, has yielded significant findings. We have explored their effectiveness in locating and efficiently blocking incoming malware, and we discuss the implications of these findings and suggest future research directions.