Microsoft Threat Intelligence Podcast cover image

Microsoft Threat Intelligence Podcast

Mark Russinovich Talks Jailbreaks

Jun 19, 2024
31:50

On this week's episode of The Microsoft Threat Intelligence Podcast, Sherrod DeGrippo is joined by Mark Russinovich.  Mark Russinovich, CTO and Technical Fellow of Microsoft Azure, joins the show to talk about his journey from developing on-prem tools like Sysinternals to working in the cloud with Azure. Sherrod and Mark discuss the evolution of cybersecurity, the role of AI in threat intelligence, and the challenge of jailbreaking AI models. Mark shares his experiences with testing AI models for vulnerabilities, including his discovery of the "Crescendo" and "Masterkey" methods to bypass safety protocols. They also touch on the issue of poisoned training data and its impact on AI reliability, while highlighting the importance of staying ahead in cybersecurity. 


In this episode you’ll learn:      

  • The shift from desktop computing to cloud-based systems and its implications 
  • Potential consequences of AI models having overridable safety instructions 
  • How AI training data can manipulate the outcomes generated by AI models 


Some questions we ask:     

  • Will AI owners be able to stop data poisoning, or will it become more common? 
  • Can you share challenges and vulnerabilities in maintaining the security of AI systems? 
  • What sparked your interest in AI jailbreaks, and what trends are you seeing? 


Resources:  

View Mark Russinovich on LinkedIn  

View Sherrod DeGrippo on LinkedIn  

 

AI jailbreaks: What they are and how they can be mitigated?

https://www.microsoft.com/en-us/security/blog/2024/06/04/ai-jailbreaks-what-they-are-and-how-they-can-be-mitigated/ 

Inside AI Security with Mark Russinovich | BRK227 

https://www.youtube.com/watch?v=f0MDjS9-dNw 

How Microsoft discovers and mitigates evolving attacks against AI guardrails.

https://www.microsoft.com/en-us/security/blog/2024/04/11/how-microsoft-discovers-and-mitigates-evolving-attacks-against-ai-guardrails/ 

Google AI said to put glue on pizza.

https://www.businessinsider.com/google-ai-glue-pizza-i-tried-it-2024-5 

 

Related Microsoft Podcasts:                   

 

Discover and follow other Microsoft podcasts at microsoft.com/podcasts  

Get the latest threat intelligence insights and guidance at Microsoft Security Insider 

 

The Microsoft Threat Intelligence Podcast is produced by Microsoft and distributed as part of N2K media network.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode