• Syed Riyazuddin Quadri
• Suvarna D. Pingle

The rapid growth of Internet of Things (IoT) devices has significantly expanded the digital ecosystem, but also increased the risk of large-scale cyberattacks. One of the most impactful threats is the MIRAI botnet, which compromises vulnerable IoT devices and launches massive Distributed Denial-of-Service (DDoS) attacks. As traditional signature-based detection methods struggle to identify evolving botnet variants, machine learning (ML) techniques have emerged as powerful alternatives for achieving high detection accuracy with minimal computational overhead. This review paper critically examines recent research contributions on MIRAI attack detection using ML algorithms. It explores datasets such as IoT-23 and N-BaIoT, highlights widely used feature extraction and preprocessing techniques, and compares the performance of algorithms including Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression, and Artificial Neural Networks (ANN). The review identifies key methodological trends, strengths, and gaps in current literature. It further discusses emerging techniques such as ensemble learning, deep learning, feature selection methods, and real-time detection frameworks for IoT edge deployment. Finally, the study outlines open issues in dataset diversity, scalability, adversarial robustness, and device heterogeneity. The paper concludes with recommendations for future work to improve generalization, reduce false alarms, and enhance resilience against evolving MIRAI variants.

IoT, Cyberattacks, MIRAI, DDoS, Random Forest.

"Detection of MIRAI Botnet Attacks Using Machine Learning Algorithms: A Comprehensive Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.h22-h25, November-2025, Available :http://www.jetir.org/papers/JETIR2511714.pdf

"Detection of MIRAI Botnet Attacks Using Machine Learning Algorithms: A Comprehensive Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. pph22-h25, November-2025, Available at : http://www.jetir.org/papers/JETIR2511714.pdf