The Azure Security Podcast Episode 108: Securing GenAI Applications with Entra
10 snips
Jan 20, 2025 Diana Vicezar, a Product Manager at Microsoft, shares her insights on securing Generative AI applications with Entra. She highlights the necessity of awareness around AI security in today's business landscape. The conversation also touches on the potential risks of AI, including unauthorized access to information. Diana emphasizes the importance of basic security practices that are often overlooked, setting the stage for a deeper exploration in future discussions about integrating security into AI applications.
AI Snips
Chapters
Transcript
Episode notes
Rethinking Security's Role
- Security should be integrated as a normal support discipline like legal or finance.
- Blaming security teams for issues caused by organizational decisions is counterproductive.
Dual Nature of AI Discovery
- AI offers powerful helpers but also risks exposing sensitive data unintentionally.
- Organizations must understand and manage AI risks, focusing on access control basics.
Unintentional AI Data Exposure
- A user’s AI assistant mistakenly shared sensitive job-related info due to lack of AI app management.
- Such unintentional AI disclosures happen when basics like access controls are not enforced.