Security and Machine Learning with Apache Spark

We have two great talks for this meetup surrounding Use Cases, Security, and Machine Learning with Apache Spark.

Agenda

18:00 - Socialize, Food, and Drink

18:30 - Detecting Advanced Adversaries with Machine Learning and Spark with Dustin Hillard

19:15 - Lessons from Spark Machine Learning Application Deployments in the Fortune 100 with Abhi Patel

Talk 1: Detecting Advanced Adversaries with Machine Learning and Spark – Dustin Hillard

We’ll discuss an approach for learning from network logs to detect anomalous and malicious behaviors on enterprise networks. Some background on Advanced Persistent Threats and the associated campaign behaviors will be presented, built on a scalable machine learning approach deployed to large customers using Spark. Learn about how data breaches like the DNC and Yahoo might be prevented in the future!

Talk 2: Lessons from Spark Machine Learning Application Deployments in the Fortune 100 – Abhi Patel

We’ll share our experiences deploying Spark applications to Fortune 100 customers. Lessons learned about the variations across different customers, what kind of clusters are typical, and how a custom application behaves in different environments. We’ll also discuss some best practices we’ve learned about successful data science in the wild on noisy customer data!