Mei Wang

Evaluating Explainability-Guided Feature Compression for Network Intrusion Detection: A Comparative Study of SHAP, Mutual Information, and RF Gain

Network intrusion detection systems (IDS) typically rely on high-dimensional feature spaces that introduce redundancy and computational overhead. While explainable AI (XAI) techniques such as SHAP have been applied to interpret IDS decisions, their utility for principled feature compression remains underexplored. This...