Optimizing Malware Detection with Random Forest, XGBoost, LightGBM, and LLM-Reporting

This study presents a comprehensive framework for malware detection that integrates traditional machine learning algorithms with advanced large language models (LLMs) to enhance both classification accuracy and automated report generation. The proposed approach leverages three widely used machine learning models-Random Forest, XGBoost, and LightGBM-to classify different types of malwares based on extracted features from the EMBER dataset, a well-known benchmark dataset for malware analysis. Each of these models was trained and evaluated to determine their effectiveness in identifying malicious software with high accuracy. Among the tested algorithms, LightGBM exhibited the best performance, achieving an impressive classification accuracy of 83%. XGBoost followed closely with 81%, while Random Forest achieved an accuracy of 79%. To further enhance the usability of the system for cybersecurity analysts, the study incorporates a large language model, specifically LLaMA, which is accessed via an API. This model is employed to generate detailed, human-readable reports that provide insights into detected malware threats. By automating the reporting process, the framework aims to reduce the manual effort required for malware analysis, allowing security professionals to focus on high-priority threats. Future research will focus on improving classification performance through advanced feature engineering techniques and exploring deep learning-based neural network architectures to further enhance the accuracy and efficiency of malware detection and analysis.