• Syed Riyazuddin Quadri
• Suvarna D. Pingle

The rapid expansion of Internet of Things (IoT) ecosystems has significantly increased the risk of large-scale cyberattacks, particularly those driven by botnets such as MIRAI. MIRAI remains one of the most dominant IoT malware families due to its ability to exploit weak device security, propagate rapidly, and launch coordinated Distributed Denial-of-Service (DDoS) attacks. This paper presents a complete implementation framework for MIRAI attack detection using machine-learning models applied to the IoT-23 dataset. The proposed system includes systematic preprocessing, feature extraction, correlation-based feature selection, and classification using Random Forest, XGBoost, Support Vector Machine (SVM), and Logistic Regression. The pipeline was developed in Python using Pandas, Scikit-Learn, and Matplotlib. Experiments demonstrate that Random Forest achieves superior performance with 99.21% accuracy, 99.10% precision, 99.16% recall, and 99.13% F1-score, outperforming other algorithms. Comparative evaluation, confusion matrices, ROC-AUC curves, and feature importance analysis validate the robustness of the model. The results highlight Random Forest as a reliable method for real-time detection of MIRAI botnet traffic and demonstrate its potential for deployment in IoT gateways and security appliances.

MIRAI, IoT-23, Random Forest, SVM, Logistic Regression.

"Machine Learning-Based Detection of MIRAI Botnet Attacks Using IoT-23 Dataset: Implementation, Evaluation, and Performance Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.a685-a689, December-2025, Available :http://www.jetir.org/papers/JETIR2512091.pdf

"Machine Learning-Based Detection of MIRAI Botnet Attacks Using IoT-23 Dataset: Implementation, Evaluation, and Performance Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 12, page no. ppa685-a689, December-2025, Available at : http://www.jetir.org/papers/JETIR2512091.pdf