Exploiting Multi-class Probabilities for solving Network Security Anomalies using Supervised and UnSupervised Machine Learning Approaches

Abstract: In this talk we understand how the probabilities of a multi classification can be exploited to identify variations in sequence of events (SoE) that eventually leads to the identification of Network level attacks. This approach initially uses a supervised multi classification, following that with an unsupervised approach to identify anomalies; what we see are everyday, simple machine learning approaches, but powerful to identify network attacks and anomalies.

Bio: Ashrith Barthur is the Principal Security Scientist at H2O currently working on algorithms that detect anomalous behaviour in user activities, network traffic, attacks, financial fraud and global money movement.

He has a PhD from Purdue University in the field of information security, specialized in Anomalous behaviour in DNS protocol.

Open Data Science Conference