Volume 10 | Issue 1 | March 2025

 Your Paper Publication Details:

 Abstract

The rapid increase in cyber threats and sophisticated attacks necessitates the development of advanced security mechanisms to safeguard networks. Traditional Intrusion Detection Systems (IDS) rely on signature-based and anomaly-based approaches, which often struggle with detecting new and evolving threats. AI-based IDS leverage Machine Learning (ML) and Deep Learning (DL) algorithms to enhance the detection of malicious activities, improve adaptability, and reduce false positives. This review provides a comprehensive analysis of AI-driven IDS, covering various methodologies such as supervised learning, unsupervised learning, and deep learning-based approaches. It also explores commonly used datasets, evaluation metrics, and the advantages of AI-driven detection mechanisms over traditional methods. Despite significant progress, AI-based IDS face challenges such as high false positive rates, adversarial attacks, scalability issues, and concept drift. We also discuss future research directions, including federated learning, explainable AI, hybrid models, and edge computing-based IDS, which can further improve the security and efficiency of intrusion detection systems. This review aims to serve as a valuable resource for researchers and practitioners in network security, highlighting the potential of AI-based IDS in mitigating cyber threats effectively.

 Keywords

Intrusion Detection System (IDS), Cyber security, Deep Learning (DL), Machine Learning (ML), Cyber Threats, Supervised, Unsupervised, and reinforcement learning.

 Authors and Affiliations

Monika Thakur
M.Tech. Scholar, Department of Computer Science & Engineering, Eklavya University, Damoh, Madhya Pradesh, India
Akanksha Jain
M.Tech. Scholar, Department of Computer Science & Engineering, Eklavya University, Damoh, Madhya Pradesh, India
Saleha Khan
M.Tech. Scholar, Department of Computer Science & Engineering, Eklavya University, Damoh, Madhya Pradesh, India
Dr. Prashant Sen
Associate professor & Head, Department of Computer Science & Engineering, Eklavya University, Damoh, Madhya Pradesh, India

 References

1. Buczak, A. L., & Guven, E. (2016). A survey of data mining and machine learning methods for cybersecurity intrusion detection. IEEE Communications Surveys & Tutorials, 18(2), 1153-1176.
2. Gao, J., Liu, Z., & Dai, Y. (2020). An overview of machine learning-based intrusion detection technology. Future Internet, 12(9), 156.
3. Wang, J., Lu, P., & Zhang, H. (2018). An efficient intrusion detection model based on machine learning. Computers & Security, 78, 1-13.
4. Zhang, C., Luo, J., & Liu, P. (2019). Deep learning-based anomaly detection in network traffic. IEEE Transactions on Network and Service Management, 16(3), 1031-1042.
5. Kumar, R., Raj, J., & Singh, A. (2021). A hybrid IDS model using machine learning techniques. Journal of Cyber Security and Mobility, 10(1), 1-20.
6. Aminanto, M. E., & Kim, K. (2018). Deep learning in intrusion detection system: A comprehensive review. Journal of Information Security and Applications, 41, 79-98.
7. Shone, N., Ngoc, T. N., Phai, V. D., & Shi, Q. (2018). A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(1), 41-50.
8. Javaid, A., Niyaz, Q., Sun, W., & Alam, M. (2016). A deep learning approach for network intrusion detection system. EAI Endorsed Transactions on Security and Safety, 3(9), e2.
9. Kim, T., Won, D., & Lee, S. (2020). LSTM-based anomaly detection for network security. IEEE Transactions on Information Forensics and Security, 15, 2598-2612.
10. Tang, T., Li, J., & Zhang, X. (2019). An LSTM-based model for network anomaly detection. Security and Communication Networks, 2019, 1-10.
11. Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2), 1-19.

  License

Creative Commons Attribution 4.0 and The Open Definition

Article Preview