))
Protecting AI at the Edge with David Weston
Manage episode 485405770 series 3659675
Content provided by Bruce Bracken. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Bruce Bracken or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
In this episode of The BlueHat Podcast, host Nic Fillingham and Wendy Zenone share David Weston’s keynote from BlueHat India 2025. David explores the growing role of on-device AI in Windows, the security risks it introduces, and how Microsoft is rethinking architecture to defend against new threats like model tampering, data exfiltration, and AI-powered malware. He also shares insights on innovations like Windows Recall, biometric protection, and the future of secure, agentic operating systems.
In This Episode You Will Learn:
How AI integration in Windows (like Windows Recall and MS Paint) is evolving
Emerging threats from protocols like MCP and CUAs
What a “confused deputy” attack is, and how Microsoft is protecting users
Some Questions We Ask:
What are the biggest security threats in on-device AI—data, model, or runtime?
Can AI be used to accelerate post-compromise attacks?
What will it take to bring Azure-level confidential computing to the consumer device?
Resources:
View Nic Fillingham on LinkedIn
Related Microsoft Podcasts:
Discover and follow other Microsoft podcasts at microsoft.com/podcasts
The BlueHat Podcast is produced by Microsoft and distributed as part of N2K media network.
57 episodes
Share
