Protecting Machine Learning Systems
In this episode, hosts Nic Fillingham and Natalia Godyla speak with Sharon Xia, a principal program manager for cloud and AI at Microsoft, about the role machine learning plays in security. They discuss four major themes, outlined in the Microsoft Digital Defense Report, including how to prepare your industry for attacks on machine learning systems, preventing attack fatigue, democratizing machine learning and leveraging anomaly detection for post-breach detection.
Then they speak to Emily Hacker, a threat intelligence analyst at Microsoft, about her path from professional writing to helping find and stop attacks.
In This Episode, You Will Learn:
- How to prepare for attacks on machine learning systems
- The dangers of a model poisoning attack
- Why it’s important to democratize machine learning
- How a humanities background helps when tracking threats
- The latest methods attackers are using for social engineering
Some Questions We Ask:
- Why are most organizations not prepared for ML attacks?
- How do you assess the trustworthiness of an ML system?
- How can machine learning reduce alert fatigue?
- What kind of patterns are analysts seeing in email threats?
- Why is business email compromise treated differently than other threats?
Resources:
Microsoft Digital Defense Report, September 2020
Related:
Listen to: Afternoon Cyber Tea with Ann Johnson
Listen to: Security Unlocked: CISO Series with Bret Arsenault
Discover and follow other Microsoft podcasts at microsoft.com/podcasts
Security Unlocked is produced by Microsoft and distributed as part of The CyberWire Network.
