IoT Intrusion Detection: Beyond Accuracy to Explanation Cost and Stability

A new study published on arXiv evaluates machine learning models for Internet of Things (IoT) intrusion detection, focusing beyond just accuracy to include explanation cost, stability, and utility. Researchers constructed a leakage-safe CICIoT2023 corpus and tested models like Logistic Regression, Decision Tree, Random Forest, and XGBoost. The findings indicate that XGBoost offers strong predictive performance, while Random Forest yields the lowest false-positive rates. The study also quantifies the computational cost of explanation generation using TreeSHAP, revealing significant differences between models and highlighting the importance of these factors for practical, resource-aware IoT security. AI

RANK_REASON The item is an academic paper detailing a study on machine learning models for intrusion detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• CICIoT2023
• decision tree
• Internet of Things
• logistic regression model
• random forest
• TreeSHAP
• XGBoost

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →