• Dr. Akhilesh Kumar

In the dynamic digital environment, cyber-attacks are a major threat to data security and system integrity. This study introduces a strong framework for the detection and classification of cyber-attacks using hybrid cryptography fused with machine learning (ML). The system integrates symmetric and asymmetric cryptography for securing data transmission while utilizing XG-Boost and Random Forest classifiers for real-time threat identification. Experiments were performed using the ToN-IoT and BoT-IoT datasets with data preprocessing, feature extraction through Extra-Tree Classifier, and performance measurement using A_accuracy, P_precision, R_recall, and 〖F1〗_score as metrics. Outcomes show that the Random Forest approach performs better than XG-Boost with 99.89% accuracy on the BoT-IoT dataset, with better precision, recall, and F1-scores than current methodologies. The integration of ML and cryptography reinforces system robustness, prevents advanced attacks, and guarantees secure data sharing, providing an encouraging solution to present-day cyber-security issues.

Cyber-attack, ML, Cryptography, XG-Boost, Random Forest

"Cyber-Attack Detection and Classification for Data Security Using Hybrid Cryptography and Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.b523-b538, July-2025, Available :http://www.jetir.org/papers/JETIR2507162.pdf

"Cyber-Attack Detection and Classification for Data Security Using Hybrid Cryptography and Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. ppb523-b538, July-2025, Available at : http://www.jetir.org/papers/JETIR2507162.pdf