Automated Threat Correlation Using Machine Learning: A Framework for Enhanced Cybersecurity

• Author(s): Feyisayo Ogunmade
• Paper ID: 1706635
• Page: 83-91
• Published Date: 11-12-2024
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 6 December-2024

Abstract

As cyber threats grow increasingly sophisticated, the demand for agile, accurate, and automated methods to detect and respond to attacks has become imperative. This paper proposes a novel machine learning-driven framework for automated threat correlation, aimed at enhancing real-time threat detection and minimizing the manual oversight often required in traditional cybersecurity measures. By leveraging advanced algorithms, such as k-means clustering for event grouping, neural networks for pattern recognition, and the Apriori algorithm for association rule mining, the framework is designed to correlate threats from diverse data sources, including network traffic logs and threat intelligence feeds. This integration of machine learning models enhances detection accuracy, reduces false positives, and accelerates response times, significantly improving resource allocation for cybersecurity teams. The proposed framework also addresses key challenges in data preprocessing, model selection, and privacy compliance, demonstrating its potential for scalability and adaptability to various threats. Comparative analysis with prior approaches highlights the framework’s efficiency in reducing detection latency and improving resilience against multi-stage cyberattacks. This work concludes with recommendations for future enhancements, such as incorporating deep learning models and expanding data sources, to further refine the framework's capabilities. The proposed machine learning-based approach for automated threat correlation represents a critical advancement in cybersecurity, providing organizations with an adaptive, resilient, and scalable solution.

Keywords

Cybersecurity, Machine Learning, Threat Correlation, Automated Detection, Clustering, Neural Networks, Real-Time Threat Detection, Data Preprocessing, False Positives, Cyber Threat Intelligence

Citations

IRE Journals:
Feyisayo Ogunmade "Automated Threat Correlation Using Machine Learning: A Framework for Enhanced Cybersecurity" Iconic Research And Engineering Journals Volume 8 Issue 6 2024 Page 83-91

IEEE:
Feyisayo Ogunmade "Automated Threat Correlation Using Machine Learning: A Framework for Enhanced Cybersecurity" Iconic Research And Engineering Journals, 8(6)