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 | Towards Green Cybersecurity: An Explainable AI Framework for Energy-Efficient Intrusion Detection |
|---|---|
| ABSTRACT | The growing use of artificial intelligence (AI) in cybersecurity has improved automated intrusion detection, but model complexity can increase computational cost and energy consumption. This paper presents a Green Explainable AI Intrusion Detection System (Green-XAI-IDS) that combines machine-learning-based intrusion detection, SHAP-based explainability, selective explanation generation, and energy-oriented evaluation. The supplied experimental results were obtained on the UNSW-NB15 benchmark using Random Forest, Gradient Boosting, and a Multi-Layer Perceptron (MLP). On the current test output, Random Forest and Gradient Boosting both report 100% accuracy, precision, recall, and F1-score. MLP reports 83.19% accuracy, 85.54% precision, 83.19% recall, and 0.826 F1-score. Gradient Boosting has the lowest measured inference time (0.1091 s), lowest energy per sample (0.00006046), and smallest model size (0.07795 MB). Selective XAI generated 1,186 explanations from 82,332 predictions, corresponding to an explanation rate of 1.44%. SHAP analysis shows `attack_cat` as the dominant feature. This result is also the principal methodological limitation of the current experiment: `attack_cat` should be excluded when it is used as information derived from the attack category or target for binary detection. Therefore, the numerical results in this paper are reported exactly as produced by the supplied experiment, but the perfect tree-model scores must be regarded as preliminary until a leakage-free rerun is completed. |
| AUTHOR | SAHANA M M, KARANVIR KAUR Assistant Professor, Department of Master of Computer Applications, Koshys Institute of Management Studies, Bengaluru, India |
| VOLUME | 188 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1409007 |
| pdf/7_Towards Green Cybersecurity An Explainable AI Framework for Energy-Efficient Intrusion Detection.pdf | |
| KEYWORDS | |
| References |
[1] A. Khraisat, I. Gondal, P. Vamplew, and J. Kamruzzaman, “Survey of intrusion detection systems: Techniques, datasets and challenges,” Cybersecurity, vol. 2, no. 20, 2019. [2] N. Moustafa and J. Slay, “UNSW-NB15: A comprehensive data set for network intrusion detection systems,” in Proc. Military Communications and Information Systems Conference (MilCIS), 2015, pp. 1–6. [3] I. Sharafaldin, A. H. Lashkari, and A. A. Ghorbani, “Toward generating a new intrusion detection dataset and intrusion traffic characterization,” in Proc. ICISSP, 2018, pp. 108–116. [4] E. Strubell, A. Ganesh, and A. McCallum, “Energy and policy considerations for deep learning in NLP,” in Proc. ACL, 2019, pp. 3645–3650. [5] R. Schwartz, J. Dodge, N. A. Smith, and O. Etzioni, “Green AI,” Communications of the ACM, vol. 63, no. 12, pp. 54–63, 2020. [6] A. B. Arrieta et al., “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Information Fusion, vol. 58, pp. 82–115, 2020. [7] M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–1144. [8] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems, 2017. [9] S. Roy, S. Sankaran, and M. Zeng, “Green intrusion detection systems: A comprehensive review and directions,” Sensors, vol. 24, no. 17, 5516, 2024. [10] Z. Ahmad et al., “Network intrusion detection system: A systematic study of machine learning and deep learning approaches,” Transactions on Emerging Telecommunications Technologies, vol. 32, no. 1, e4150, 2021. [11] M. Tavallaee, E. Bagheri, W. Lu, and A. A. Ghorbani, “A detailed analysis of the KDD CUP 99 data set,” in Proc. IEEE CISDA, 2009. |
