Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
A Comprehensive Forecasting-Based Framework for Time Series Anomaly Detection: Benchmarking on the Numenta Anomaly Benchmark (NAB)
Mohammad Karami, Mostafa Jalali, Fatemeh Ghassemi
Time series anomaly detection is critical for modern digital infrastructures, yet existing methods lack systematic cross-domain evaluation. We present a comprehensive forecasting-b…
cs.LG2025
OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting
Mohammad Karami, Fatemeh Ghassemi, Hamed Kebriaei +1
Federated Learning (FL) enables collaborative model training across distributed medical institutions while preserving patient privacy, but remains vulnerable to Byzantine attacks a…