Efficient Botnet Attack Detection using Machine Learning Models

Abstract- As the number of cyber threats continues to rise, botnet attacks have become a significant concern in the field of network security. This study aims to create an effective botnet attack detection system using machine learning models, with a particular emphasis on boosting techniques like XGboost, ADAboost, CATboost, Gradient boosting, and LightGBM. These models are assessed using accuracy, precision, recall, and f1-score to identify the most effective approach. The system goes through a thorough process of feature engineering and data preprocessing to improve its ability to detect objects. By utilizing ensemble learning, the proposed framework enhances the accuracy of detecting botnet attacks while minimizing false positives and achieving high detection rates. The algorithm is a valuable tool for cybersecurity applications, as it can detect and prevent malicious activities.