Dimitrios Pezaros

Heterogeneous Graph Fusion for Multi-Modal Industrial Anomaly Detection

Multi-agent reinforcement learning for DoS mitigation in industrial control systems

A multi-agent reinforcement learning (MARL) framework that utilises software-defined networking (SDN) to achieve near real-time mitigation of DoS attacks targeting ICS networks, and exploits the scalability benefits of hierarchical learning to provide more granular agent decision making through a composite action space...

Charon: Stratified Priority Sampling for Differentiated Per-Flow Measurement in High-Speed Networks

Charon, a priority-aware sketch that replaces the structural separation used by prior methods with stratified admission sampling, achieves more than 2× higher detection accuracy for high-priority flows than the best baseline and up to four orders of magnitude lower average error than state-of-the-art priority-aware ske...