Breaking AI to Build Trust: A Conversation with a Microsoft Red Team Engineer
In this episode of the Microsoft Innovation Podcast, Joris De Gruyter, Senior Offensive Security Engineer at Microsoft, discusses AI security. The AI Red Team at Microsoft tests and breaks AI systems to ensure safety and trustworthiness. They test for vulnerabilities, jailbreaks, harmful content generation, data exfiltration, and bias. The team consists of members with diverse backgrounds and prioritizes mental health support. De Gruyter recommends hands-on experimentation for developing AI skills and curating your own information sources. The episode also mentions the new show, The AI Advantage, and promotes the DynamicsMinds event in Slovenia. Additionally, the 90 Day Mentoring Challenge is highlighted as a way to accelerate a career in the Microsoft Power Platform and Dynamics 365 ecosystem.
Podcast 5w
Login now to access my digest by 365.Training
Learn how my digest works
Features
- Articles, blogs, podcasts, training, and videos
- Quick read TL;DRs for each item
- Advanced filtering to prioritize what you care about
- Quick views to isolate what you are looking for right now
- Save your favorite items
- Share your favorites
- Snooze items you want to revisit when you have more time