Machine Learning Enables Malware Detection and Classification Techniques

Malware developers and security analysts engage in a never-ending and continuous battle as malware complexity changes in tandem with technological advancements. This paper discusses the machine learning approaches, problems, and solutions for various malware detection and categorization. The range of threats to user privacy, computer security/data security is growing rapidly, mitigation of malware is considered by the information security sector as an important and ongoing activity that requires for effectiveness and efficiency and accuracy. It is thought that there may be more authorized software versions than there are malware variants. Every year, malware becomes a more prevalent problem, necessitating the replacement of static detection methods using machine learning. Examining the machine learning methods and approaches with various data sets and their issues with harmful behavior identification and categorization is the major goal here, researchers are benefited by understanding the classification and detection of malware. In our experiment we use various machine learning classifiers and compare the accuracy and detection time taken by classifiers.