This article is contributed. See the original author and article here.
How are we using machine learning (ML) and artificial intelligence (AI) to improve cybersecurity today? What are the different types of ML algorithms, and how do they differ? Taking it a step further, how do we protect our ML systems? According to the 2020 Microsoft Digital Defense Report, we know adversarial machine learning and attacks on ML systems are part of the future of cybersecurity. Yet, 89% percent of surveyed organizations felt they don’t have the right tools in place to secure their ML systems.
Security Unlocked is a new podcast exploring the technology and people powering Microsoft’s security solutions—co-hosted by myself and Nic Fillingham—with a special emphasis on ML and AI. We tackle these questions in interviews with security experts across Microsoft Security (and have a few laughs along the way).
In each episode we talk to Microsoft Security experts about the latest innovations in the intersection of threat intelligence, security research and data science. Our conversations focus on how cybsersecurity is evolving alongside threats, how our products are built and how ML and AI are truly empowering our customers. As Sharon Xia, Principal Program Manager at Microsoft , said in our most recent episode, “Security teams and machine learning teams are running on two parallel orbits.” In having a dialogue around these topics, we hope to provide information that can help change that.
In each episode we also interview one of the security experts working in Microsoft Security to hear their career story and their perspectives on ML and AI and the future of cybersecurity. Today, security professionals come from a range of disciplines and backgrounds, bringing with them new perspectives and approaches. We aim to highlight the unique community of people making the world a more secure place.
We encourage you to share feedback or suggestions on topics via @MSFTSecurity or by emailing us at SecurityUnlocked@microsoft.com! We want to hear from you!
Here’s a line-up of a few of our most recent episodes:
Protecting Machine Learning Systems
Guests: Sharon Xia and Emily Hacker
In this episode, we chat with Sharon Xia, Principal Program Manager at Microsoft, on the rising tide of machine learning in security—from the different types of machine learning attacks to the application of machine learning in security solutions to the democratization of ML. We also chat with Emily Hacker, threat analyst at Microsoft, to learn how she went from English major to security analyst. Listen here.
How to Catch a Villain with Math
Guests: Mike Flowers, Cole Sodja, Justin Carroll and Dr. Anna Bertiger
In this episode we chat with Mike Flowers and Cole Sodja of the Microsoft Protection Team and Justin Carroll of the Microsoft Threat Intelligence Global Engagement and Response team. Our three experts explain how they’re using machine learning to identify and model lateral movement attacks. We also speak with Dr. Anna Bertiger, Senior Applied Scientist at Microsoft, to learn ow she’s using math to catch villains. Listen here.
Brought to you by Dr. Ware, Microsoft Office 365 Silver Partner, Charleston SC.