Copyright © 2026 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{204543,
        author = {Mizpah T and D K Kalai Vani},
        title = {An Integrated Hybrid AI Approach for Cyber Attack Prediction with Machine Learning and Generative Artificial Intelligence},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {3010-3018},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204543},
        abstract = {The complexity of cyber threats is increasingly becoming a challenge to the old system of intrusion detection since most of them are not flexible and interpretable. To avoid this, a combined cybersecurity framework is suggested that is based on machine learning, deep learning, generative models, and explainable artificial intelligence to detect threats accurately and in a transparent way. The methodology is preprocessing of data, feature engineering, training the model and synthetic data generation involving generative adversarial networks to address the issue of class imbalance. Explainable AI has been included to bring out interpretable insights about decision-making in models. The experimental outcomes indicate that the suggested method has a high accuracy, better precision and recall, and high generalization. It is also applicable in predicting cyber threats in real-time in a dynamic network setting because the framework is capable of increasing the detection reliability without compromising the transparency levels.},
        keywords = {Cybersecurity, Intrusion Detection, Machine Learning, Deep Learning, Explainable Artificial Intelligence, Generative Models, Threat Detection, Network Security.},
        month = {June},
        }