Cybercrime is the fastest growing crime and perhaps the greatest threat to every company in the world. It is increasing in size, sophistication, and cost. It is projected that cybercrime will cost the world $6 trillion annually by 2021. This represents the greatest transfer of economic wealth in history, risks the incentives for innovation and investment.

In this talk, we will address techniques to detect malicious cyber activities. In principle, anomaly-based approaches can be used to find these activities for known attacks. However, how do you detect attacks that are unknown to experts? We show how AI can be used to create a self-learning system and find attacks that were previously unknown to cyber experts. We use real data to illustrate these methods to show how to catch hackers!