Automating Threat Intelligence: The Use of AI in Cyber Threat Prediction and Mitigation

Vishwakarma, Aniket (2025) Automating Threat Intelligence: The Use of AI in Cyber Threat Prediction and Mitigation. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (684kB) | Preview
Preview	PDF (Configuration Manual) Download (378kB) | Preview

Abstract

The proliferation of digital services and the increasing sophistication of cyber attacks have rendered traditional, signature-based security systems insufficient for modern threat landscapes. This research project addresses the critical need for proactive and automated threat intelligence by leveraging Artificial Intelligence (AI) and Machine Learning (ML). The core objective is to design, implement, and evaluate an end-to-end system capable of predicting and classifying diverse cyber threats from network traffic data in near real time. This study utilizes a comprehensive dataset featuring various network attacks, including Denial of Service (DoS), Distributed Denial of Service (DDoS), Port Scanning, and Web Attacks. A rigorous data preprocessing, feature engineering, and dimensionality reduction pipeline was developed to prepare the data for modelling. Eight distinct machine learning classifiers were benchmarked, with the Random Forest algorithm emerging as the most effective, achieving an F1-score of 0.9756 on unseen test data. The research extends beyond model creation to encompass the full lifecycle of a production-grade AI system. The final model was encapsulated within a Flask web application, offering single, batch, and API-based prediction capabilities. The application was eventually deployed to a cloud environment on Amazon Web Services (AWS) through a fully automated Continuous Integration and Continuous Deployment (CI/CD) workflows that were managed by GitHub Actions. The results show that an AI driven approach can offer accurate automated classification of threats, which can potentially greatly increase the capability of an organization to be proactive in its mitigation of cyber threats. The deployed system serves as a real-world example of a way to incorporate cutting edge AI into a proactive cyber security environment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Salahuddin, Jawad UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	17 Jun 2026 09:34
Last Modified:	17 Jun 2026 09:34
URI:	https://norma.ncirl.ie/id/eprint/9382

Actions (login required)

View Item