Volume : 12, Issue : 2, FEB 2026

A LIGHTWEIGHT MACHINE LEARNING FRAMEWORK FOR REAL-TIME CYBERATTACK DETECTION IN RESOURCE-CONSTRAINED ENVIRONMENTS

SUMANDEEP KAUR, DR. GEETANJALI

Abstract

The rapid growth of interconnected systems, cloud computing, and Internet of Things (IoT) infrastructures has significantly increased the attack surface of modern networks. Cyberattacks have become more frequent, diverse, and sophisticated, posing serious threats to data confidentiality, integrity, and availability. While machine learning and deep learning-based intrusion detection systems have demonstrated high detection accuracy, they often require extensive computational resources, large memory footprints, and long inference times, making them unsuitable for real-time and resource-constrained environments.

This research presents a lightweight machine learning framework for real-time cyberattack detection that emphasizes efficiency, adaptability, and scalability. The proposed framework integrates optimized feature selection, hybrid lightweight classifiers, and online learning mechanisms to achieve a balance between detection accuracy and computational cost. Extensive experimental evaluation on benchmark intrusion detection datasets demonstrates that the proposed approach achieves high detection performance while maintaining low latency and reduced resource utilization. The results indicate that lightweight machine learning models can provide practical and effective cyberattack detection in modern network environments, particularly at the edge and IoT levels.

Article : Download PDF

Cite This Article

IESRJ

International Educational Scientific Research Journal

E-ISSN: 2455-295X

International Indexed Journal | Multi-Disciplinary Refereed Research Journal

ISSN: 2455-295X

Peer-Reviewed Journal - Equivalent to UGC Approved Journal

Peer-Reviewed Journal

Article No : 6

Number of Downloads : 90

References

1. Kumar, A., and Singh, M., Efficient Machine Learning Techniques for Intrusion Detection, Journal of Cybersecurity Research, 2022.

2. Li, T., Zhang, Y., and Chen, H., Online Learning Methods for Network Security, IEEE Transactions on Network and Service Management, 2023.

3. Patel, S., Lightweight Intrusion Detection Models for IoT Networks, International Journal of Information Security, 2024.

4. Brown, L., Adaptive Cyber Defense Systems, ACM Computing Surveys, 2023.