The Azure Security Podcast

Episode 90: AI Red Teaming

Jan 29, 2024
The podcast covers a range of interesting topics, including AI Red Teaming and the concept of 'jail-breaking' large language models. They discuss the interplay between language and AI models, as well as the importance of red teaming and mitigating risks in AI. Updates on security for Azure SQL and SQL Server are also provided.
Ask episode
Chapters
Transcript
Episode notes
1
Introduction
00:00 • 4min
2
Security Updates for Azure SQL and SQL Server, Upgrade to Gen2 Trusted Launch, Key Support for Azure NetApp Files, and more
04:02 • 3min
3
AI Red Teaming: Scope, Skills, and Interconnections
07:09 • 10min
4
Exploring the Concept of Co-Pilot and its Role in Microsoft's GNAI Products
17:39 • 2min
5
Exploring the Concept of 'Jail-breaking' Large Language Models
19:32 • 2min
6
The Interplay Between Language and AI Models
21:40 • 9min
7
The Importance of Red Teaming and Mitigating Risks
30:49 • 8min