Abstract: The modern networks have become more complex making it difficult to detect anomalies in real time and reduce congestion. Conventional machine learning models, however precise, are black boxes, which do not provide much information about the way they make decisions. To solve this, Explainable Artificial Intelligence (XAI) offers transparency, interpretability and accountability in network monitoring. This paper locate, assess and contrast XAI methods used in network anomaly detection with a particular focus on model transparency and point out the research.....
Key Word: Explainable AI, Network Anomaly Detection, SHAP, LIME, Grad-CAM, Network Optimization
[1].
Aysel, H. I., Cai, X., & Prugel-Bennett, A. (2025). Explainable Artificial Intelligence: Advancements and Limitations. Applied Sciences, 15(13), 7261.
[2].
Beckley, J. (2025). Advanced risk assessment techniques: Merging data-driven analytics with expert insights to navigate uncertain decision-making processes. Int J Res Publ Rev, 6(3), 1454-1471.
[3].
Gummadi, A. N., Napier, J. C., & Abdallah, M. (2024). XAI-IoT: an explainable AI framework for enhancing anomaly detection in IoT systems. IEEE Access, 12, 71024-71054.
[4].
Han, Y., Huang, G., Song, S., Yang, L., Wang, H., & Wang, Y. (2021). Dynamic neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(11), 7436-7456.
[5].
Hnamte, V., Najar, A. A., Nhung-Nguyen, H., Hussain, J., & Sugali, M. N. (2024). DDoS attack detection and mitigation using deep neural network in SDN environment. Computers & Security, 138, 103661..
