Defense Against the Dark Bots: How Microsoft Protects 1 Billion Users with Machine Learning
With the rise of mobile applications, social media, online gaming and collaboration software, all of us use our online identities in the cloud every day. At Microsoft, we enable 1 billion people every month to work and play using Microsoft online accounts. Criminals have followed users to the cloud, and it has become easier than ever to profit at low risk from compromising online identities. Finding these malicious actors among terabytes of data daily is no easy task. We rely on Machine Learning and other advanced data-driven techniques to find the bad among large amounts of user activity. Our algorithms have to be robust, fast and accurate. In this talk we’ll discuss the major attacks we see and how we apply Machine Learning to find the attackers and keep 1 billion users safe.
Lunch will be served and registration is required.
Friday, October 18, 2019
Alex is the Director of Identity Security for Microsoft. Billions of users sign in to millions of apps almost 20 billion times per day on Microsoft’s Identity platform. The Identity Security team protects users from unauthorized access, account takeover and abuse. If you have signed into Xbox, Skype, Outlook, Office 365, Azure, Dynamics or any number of our B2C sites or organizations using Azure AD, we’re the team standing between you and the hackers. In addition to detection, investigation and response, the Identity Security team delivers products including Azure AD Multi-Factor Authentication, Identity Protection, Conditional Access, and the Authenticator App, as well as a host of enterprise and consumer account defense systems. Prior to his current role, Alex served in a variety of engineering and product management roles on products such as MSN, Visual Studio, Xbox, and Identity related products like Active Directory. Outside of work, Alex is passionate about interfacing with various humans, making stuff, sailing, and music.
Maria Puertas Calvo
Maria Puertas Calvo leads Microsoft’s Identity Security and Protection data science team. She focuses on improving the intelligence behind Azure AD Identity Protection and all Microsoft Account prevention and detection systems. Her work translates into constant improvements of the Machine Learning algorithms that keep Microsoft users secure and protected. Before Identity, she worked on detecting spam on Outlook.com. Maria has a Master’s in Computer Science from the Autonomous University of Madrid, Spain, where she also did academic research in biometrics and Machine Learning.