Evaluation of Explainable Artificial Intelligence in IoT Intrusion Detection Systems Under DeepFool Adversarial Conditions
As IoT systems complexity grows, transparent and trustworthy machine-learning intrusion detection systems are crucial. Post hoc explainable AI methods, such as SHAP and LIME, are the most widely used ways to explain how models work, but the degree to which these methods are robust to adversarial con...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
MDPI AG
2026-05-01
|
| Schriftenreihe: | Sensors |
| Schlagworte: | |
| Online-Zugang: | https://www.mdpi.com/1424-8220/26/10/2924 |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|