Real-time Anomaly Detection in IoT Network Traffic
Smart environments equipped with IoT devices are increasingly under threat from an escalating number of sophisticated cyber-attacks. Unfortunately, current security approaches are inaccurate, expensive, or unscalable, as they require static signatures of known attacks, specialized hardware, or full packet inspection.
The student will analyze network traffic of IoT devices, assess their security and privacy posture, and develop models to learn their behavior. Particular attention should be aimed at timely anomaly detection, i.e., detecting threats in real-time.