Microsoft Mechanics Podcast24 Okt 2024

AI apps - Control Safety, Privacy & Security - with Mark Russinovich

What are prompt injection attacks and how do you stop them? How do you avoid deceptive responses? Can AI traffic be end-to-end encrypted? We'll answer these questions and more with technical demonstrations to make it real.

Mark Russinovich will show you how to develop and deploy AI applications that prioritize safety, privacy, and integrity. Leverage real-time safety guardrails to filter harmful content and proactively prevent misuse, ensuring AI outputs are trustworthy. The integration of confidential inferencing enables users to maintain data privacy by encrypting information during processing, safeguarding sensitive data from exposure. Enhance AI solutions with advanced features like Groundedness detection, which provides real-time corrections to inaccurate outputs, and the Confidential Computing initiative that extends verifiable privacy across all services.

Mark Russinovich, Azure CTO, joins Jeremy Chapman to share how to build secure AI applications, monitor and manage potential risks, and ensure compliance with privacy regulations.

► QUICK LINKS:
00:00 - Keep data safe and private
01:19 - Azure AI Content Safety capability set
02:17 - Direct jailbreak attack
03:47 - Put controls in place
04:54 - Indirect prompt injection attack
05:57 - Options to monitor attacks over time
06:22 - Groundedness detection
07:45 - Privacy—Confidential Computing
09:40 - Confidential inferencing Model-as-a-service
11:31 - Ensure services and APIs are trustworthy
11:50 - Security
12:51 - Web Query Transparency
13:51 - Microsoft Defender for Cloud Apps
15:16 - Wrap up

► Link References

Check out https://aka.ms/MicrosoftTrustworthyAI

For verifiable privacy, go to our blog at https://aka.ms/ConfidentialInferencing

► Unfamiliar with Microsoft Mechanics?

As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.

• Subscribe to our YouTube: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(100)

Windows 365: Five Years In, See What's New

An AI agent works inside your Windows 365 Cloud PC from a Teams chat on your phone — finding downloaded files, editing documents, and drafting emails with your laptop lid closed. Microsoft Scout, a ne...

21 Aug 15min

Build your first Power App from data in seconds

Build a fully working model-driven app from your existing Dataverse, SharePoint, or SQL data in under a minute — screens, navigation, and forms included. Generate new pages from a natural language pro...

16 Jul 7min

Microsoft Entra Suite hands-on tour of identity and network access protections

Unify identity and network access controls. Enforce least privilege access across every app and resource. Wire lifecycle workflows directly to your HR system to strip stale permissions on role changes...

15 Jul 9min

New agentic platform in Dynamics 365 for Sales and Service

Qualify a lead, close a case, or walk into a renewal meeting fully briefed, all from the sales and service agents built into Dynamics 365. Ask a question and pull a grounded answer straight from your ...

14 Jul 10min

Tokenomics | The new AI currency & your options explained

Control what you're billed on. Tokens are the currency of AI, and how you design your app determines how many you spend. Compress conversation history instead of resending it raw, cap output tokens wi...

9 Jul 14min

Deploy Windows updates to counter AI-discovered threats

The speed that AI can now discover and exploit vulnerabilities means that our defenses also need to adjust. For the devices that you manage where you can afford to tighten deployment timelines, we'll ...

7 Jul 3min

Zero Trust security for AI agents

Apply Zero Trust controls to every AI agent in your environment across identity, tool usage, and data access. Extend Conditional Access in Microsoft Entra to evaluate every agent authorization request...

2 Jul 10min

Secure containers from code to runtime | Microsoft Defender

Secure containerized apps end-to-end using Microsoft Defender for Cloud. Correlate cross-cloud attacks into a single incident, catch runtime threats that image scanning misses, and block vulnerable im...

29 Jun 9min