Apt detection using ml 

Advanced Persistent Threats (APTs) represent a major challenge to modern network security due to their stealthy nature and ability to evade traditional detection mechanisms. This project presents a machine learning–based approach for detecting APT and benign network traffic using flow-level network data. A real-world dataset containing detailed traffic parameters such as packet statistics, protocol information, and timing features is utilized for model training and evaluation. Random Forest and XGBoost algorithms are employed to achieve accurate and reliable classification. The system is implemented using Python and Flask for backend processing, along with a web-based interface developed using HTML, CSS, and JavaScript for user interaction. Experimental results demonstrate that the proposed system enhances detection accuracy and provides an efficient, scalable solution for intelligent APT detection.

Keywords: Advanced Persistent Threat (APT), Intrusion Detection System (IDS), Machine Learning, Random Forest, XGBoost, Network Traffic Analysis, Cybersecurity, Classification, Flask Web Application.