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{208753,
        author = {Tanuja and Shrushti and Nikita and Sunil Mahajan},
        title = {Cyberattack Detection Using Data Analytics and Machine Learning: A Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {649-659},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208753},
        abstract = {The rapid growth of digital networks, cloud services, Internet of Things (IoT) devices, and online applications has increased the risk of cyberattacks. Traditional cybersecurity approaches, particularly signature-based detection, are effective for known threats but may have difficulty identifying new, modified, or sophisticated attacks. Data analytics and machine learning provide promising approaches for analysing large volumes of network and security data and identifying suspicious behaviour. This paper reviews existing research on machine learning and deep learning techniques for cyberattack and network intrusion detection. Five Scopus-indexed studies are examined to understand commonly used detection approaches, datasets, algorithms, evaluation measures, and research challenges. The reviewed literature covers techniques including supervised learning, unsupervised learning, anomaly detection, deep neural networks, recurrent neural networks, convolutional neural networks, autoencoders, and ensemble-based approaches. The literature also emphasizes the importance of appropriate datasets and evaluation methods for reliable intrusion detection. The review indicates that machine learning and data analytics can support automated detection of malicious network behaviour, but challenges remain in false positives, dataset quality, changing attack patterns, computational cost, privacy, and generalization to real-world environments. The paper proposes a general data-driven framework for cyberattack detection and identifies future directions including real-time detection, adaptive learning, explainable artificial intelligence, and privacy-preserving machine learning.},
        keywords = {Cybersecurity, Cyberattack Detection, Data Analytics, Machine Learning, Intrusion Detection, Deep Learning.},
        month = {September},
        }