Integration of Machine Learning Models for Real-Time Detection of Advanced Persistent Threats and Network Intrusions
2025
This research explores the integration of machine learning (ML) models for real-time detection of Advanced Persistent Threats (APTs) and network intrusions. By leveraging supervised and unsupervised learning techniques, including anomaly detection, deep learning, and ensemble methods, the study aims to enhance cybersecurity defenses. The proposed framework incorporates feature selection, data preprocessing, and adaptive learning strategies to improve detection accuracy and reduce false positives. Real-time threat analysis is achieved through scalable ML pipelines, ensuring rapid response to evolving cyber threats. This approach enhances network security by providing proactive intrusion detection, mitigating risks, and strengthening overall cyber defense mechanisms against sophisticated attacks.