Machine Learning-Based Static Analysis for Malware Detection in Executable Files

The increasing threat of malware in the digital world necessitates robust and scalable detection systems. This paper introduces a machine learning-based malware detection system that analyzes Portable Executable (PE) files to identify malicious software. Leveraging supervised learning algorithms and feature engineering, the system achieves high accuracy in detecting harmful binaries. The Random Forest classifier, trained on a large dataset of PE files, demonstrated exceptional performance. The proposed system streamlines malware classification and can be integrated into broader cybersecurity frameworks.