Darktrace - Applying Machine Learning for Pracitcal Cyber Security

Advances in Machine Learning have led to new approaches for cyber security. Instead of focusing on low-level indicators of compromise - such as  signatures - defenders can now concentrate on anomalous activity. This talk will explore how Machine Learning is practically used on network data to detect anomalies across the whole attack lifecycle and how to use the results for threat hunting. Real-world examples of threats found in networks around the globe will be shared and a demonstration of applied unsupervised Machine Learning will be given.