Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182994,
        author = {Prof.S. M. Jawake and Mr rahul bhutada and Sunny Kamalprasad Pandey and Prof. Vrushali Gokul Telharkar and Vaishnavi Rajendra Bakal},
        title = {AI-Driven Cybersecurity: Anomaly Detection and Threat Intelligence Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {4138-4144},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182994},
        abstract = {The rapid escalation of cyber threats and the growing complexity of attack vectors require improved defense systems capable of real-time adaptation and response. This paper introduces a thorough framework for AI-based cybersecurity that utilizes machine learning methods for anomaly detection and threat intelligence. We propose a multi-tiered strategy that integrates unsupervised learning for anomaly detection, supervised learning for threat categorization, and deep learning for pattern identification in network data. Our experimental findings indicate a 94.7% accuracy in identifying zero-day assaults and a 23% decrease in false positive rates relative to conventional signature-based systems. The architecture combines real-time threat intelligence feeds with adaptive machine learning models to deliver proactive security solutions. Performance assessment on actual network datasets demonstrates substantial enhancements in threat detection velocity and precision, while preserving system efficacy.},
        keywords = {Cybersecurity, Machine Learning, Anomaly Detection, Threat Intelligence, Deep Learning, Network Security},
        month = {July},
        }