Blog
Writing about machine learning for cybersecurity, trustworthy AI, and real-world ML systems.
Energy Cost of Enhancing Reliability of ML Models for Edge IoT Security
Jan 01, 2026Improving reliability in ML-based IoT security comes at an energy cost. This work quantifies and analyzes that trade-off for edge deployments.
Read more
Towards Better-Calibrated ML Models for Reliable Network Intrusion Detection
Oct 01, 2025Calibration-aware SHAP-based feature selection improves reliability and confidence estimation for ML-based intrusion detection systems.
Read more
Reducing Complexity and Enhancing Predictive Power of ML-based Lightpath QoT Estimation
May 01, 2024SHAP-assisted feature selection reduces model complexity while improving prediction accuracy for optical network QoT estimation.
Read more