International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Explainable Deep Learning Framework for Real - Time Cyber Threat Detection and Security Risk Assessment |
|---|---|
| ABSTRACT | The emergence of advanced cyber-attacks calls for the development of accurate and understandable detection mechanisms. In this regard, the current paper suggests a novel Explainable Deep Learning Framework (XDLF) for detecting and assessing the risks posed by cybersecurity threats. The framework combines the hybrid CNN-LSTM model and SHAP-based explainability with a quantitative risk score calculation component. Tested on the CICIDS-2017 and NIDS-Bench-2026 datasets, XDLF shows high accuracy with little time needed for inferring each flow. The explainability component produces feature level attributions that help security experts comprehend the reason for detection, decreasing the mean time required for this task. It is shown in comparative analysis that XDLF surpasses other XAI-IDS systems. |
| AUTHOR | THOOMULA KAVYA SRI Lecturer, Department of Computer Science, Pratibha Degree & PG College, Siddipet, Telangana, India |
| VOLUME | 181 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1402067 |
| pdf/67_Explainable Deep Learning Framework for Real - Time Cyber Threat Detection and Security Risk Assessment.pdf | |
| KEYWORDS | |
| References |
[1] A. Aldweesh, A. Derhab, and A. Z. Emam, "Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues," Knowledge-Based Systems, vol. 189, p. 105124, Feb. 2021. [2] M. A. Ferrag, L. Maglaras, S. Moschoyiannis, and H. Janicke, "Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study," Journal of Information Security and Applications, vol. 50, p. 102419, Feb. 2021. [3] R. Kumar, P. Kumar, and R. Tripathi, "Deep learning for intrusion detection in IoT networks: A comprehensive review," Computer Science Review, vol. 45, p. 100486, Aug. 2022. [4] S. Mahdavifar and A. A. Ghorbani, "Application of deep learning to cybersecurity: A survey," Neurocomputing, vol. 347, pp. 149-176, Jun. 2021. [5] N. Moustafa, M. Ahmed, and J. Hu, "NIDS-Bench-2026: A benchmark dataset for encrypted advanced persistent threat detection," IEEE Transactions on Dependable and Secure Computing, vol. 23, no. 2, pp. 1124-1138, Mar.-Apr. 2026. [6] S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Advances in Neural Information Processing Systems, vol. 30, 2021, pp. 4765-4774. [7] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, May 2021. [8] I. Sharafaldin, A. H. Lashkari, and A. A. Ghorbani, "Toward generating a new intrusion detection dataset and intrusion traffic characterization," in Proc. 4th International Conference on Information Systems Security and Privacy, 2021, pp. 108-116. [9] W. Wang, M. Zhu, J. Wang, X. Zeng, and Z. Yang, "End-to-end encrypted traffic classification with one-dimensional convolution neural networks," in Proc. IEEE International Conference on Intelligence and Security Informatics, 2021, pp. 43-48. [10] D. Gunning, M. Stefik, J. Choi, T. Miller, S. Stumpf, and G.-Z. Yang, "XAI—Explainable artificial intelligence," Science Robotics, vol. 4, no. 37, p. eaay7120, Dec. 2021. |
