Machine Learning Approaches for Malware Detection in Cloud Portable Executable Files

A major cybersecurity threat is posed by malicious software, which is constantly changing. These novel threats are difficult for traditional signature-based detection techniques to identify. By identifying novel patterns, machine learning (ML) frameworks can enhance malware detection. This study examines malware detection using machine learning techniques with an emphasis on characteristics found in cloud Portable Executable (PE) headers. It examines several machine learning approaches, such as random forest, logistic regression, and artificial neural networks (ANN). The outcomes demonstrate the value of feature selection and algorithm tuning for high detection rates, empha- sizing machine learning's effectiveness in malware detection.