International Journal of Computer Techniques Volume 12 Issue 3 | Machine Learning for Cyber Security Review in Research Directions
Machine Learning for Cyber Security: Review in Research Directions
International Journal of Computer Techniques – Volume 12 Issue 3, May – June 2025
Abstract
This paper presents a comprehensive **literature review on machine learning applications in cybersecurity**, examining techniques used in **intrusion detection, phishing prevention, malware classification, and anomaly detection**. It identifies **key challenges, widely-used algorithms, datasets**, and outlines **future directions** such as **explainable and federated learning** to support secure, scalable, and transparent digital ecosystems.
Index Terms
Adversarial Robustness, Anomaly Detection, Cybersecurity, Explainable AI, Intrusion Detection Systems, Machine Learning, Malware Detection.
Conclusion
**Machine learning offers transformative potential for cybersecurity**, providing dynamic and proactive solutions to modern threats. This review highlights the progress in intrusion detection and malware classification while noting current gaps in data quality, model transparency, and deployment scalability. Emphasis should now shift toward developing **explainable, lightweight, and federated ML frameworks** that are robust in real-world adversarial conditions.
References
- Vinayakumar, R. et al. (2019). “Deep Learning Approach for Intelligent Intrusion Detection System.” IEEE Access, 7, 41525–41550.
- Ring, M. et al. (2019). “A Survey of Network-Based Intrusion Detection Data Sets.” Computers & Security, 86, 147–167.
- Zhang, Y. et al. (2023). “Federated Learning-Based Distributed Intrusion Detection for Edge Networks.” Future Generation Computer Systems, 139, 93–107.
Post Comment