Data Mining and Machine Learning for Analysis of Network Traffic : PLENARY TALK

Traffic traces collected from deployed communication networks have been used to characterize and determine traffic loads, analyze patterns of users’ behavior, model network traffic, and predict future network traffic. Data have been also used to analyze network topologies and capture historical trends in their development. Of particular interest to cybersecurity is detection of network anomalies and intrusions including worms, denial of service attacks, ransomware, and blackouts. Machine learning techniques have proved to be valuable tools for predicting anomalous Internet traffic behavior and for classifying various traffic routing anomalies. In described case studies, traffic traces collected from various deployed networks and the Internet are used to characterize and model network traffic, analyze Internet topologies, and classify network anomalies.