Microsoft Threat Intelligence Podcast17 Joulu 2025

Whisper Leak: How Threat Actors Can See What You Talk to AI About

In this episode of the Microsoft Threat Intelligence Podcast, host⁠ ⁠⁠Sherrod DeGrippo is joined by security researchers Geoff McDonald and JBO to discuss Whisper Leak, new research showing that encrypted AI traffic can still unintentionally reveal what a user is asking about through patterns in packet size and timing. They explain how LLM token streaming enables this kind of side-channel attack, why even well-encrypted conversations can be classified for sensitive topics, and what this means for privacy, national-level surveillance risks, and secure product design. The conversation also walks through how the study was conducted, what patterns emerged across different AI models, and the steps developers should take to mitigate these risks. In this episode you’ll learn: Why packet sizes and timing patterns reveal more information than most users realize How user-experience choices like showing streamed text create a larger attack surface The difference between classic timing attacks and the new risks uncovered in Whisper Leak Resources: View JBO on LinkedIn View Geoff McDonald on LinkedIn View Sherrod DeGrippo on LinkedIn Learn more about Whisper Leak Related Microsoft Podcasts: Afternoon Cyber Tea with Ann Johnson The BlueHat Podcast Uncovering Hidden Risks 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, Hangar Studios and distributed as part of N2K media network.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(80)

Inside this year’s Microsoft Digital Defense Report

In this episode, host Elliot Volkman is joined by Chloe Messdaghi and Karen Frost for a behind-the-scenes look at Microsoft’s annual Digital Defense Report (MDDR). They explore how AI is reshaping the...

7 Loka 36min

From Identity Compromise to AI Defense: Inside Modern Incident Response

This week we are taking you back to Black Hat USA 2026 and exploring two sides of the security landscape. First, Microsoft incident response experts Adrian Hill and Terry Mee break down identity-bas...

30 Syys 50min

Why Threat Actors Love Your RMM

In this episode of the Microsoft Threat Intelligence Podcast, recorded live at Black Hat, Microsoft Threat Intelligence Director Elliot Volkman is joined by Andrew “Spike” Brandt, Principal Threat Int...

9 Syys 28min

JADEPUFFER: An End-to-End Agentic-Led Ransomware Attack

In this episode of the Microsoft Threat Intelligence Podcast, we are joined by Sysdig’s Michael Clark and Crystal Morin to discuss JADEPUFFER, one of the first documented cases of an LLM conducting an...

26 Elo 31min

Shifts We Are Seeing Across Social Engineering, Post-Disruption Impact Report

In this episode of the Microsoft Threat Intelligence Podcast, Microsoft Threat Intelligence Director⁠ Elliot Volkman is joined by Microsoft Principal Threat Intelligence Analyst Crane Hassold to explo...

12 Elo 24min

A Farewell from Sherrod: New Season Coming Soon

As we close out season three of the podcast, Sherrod offers her farewell message as she takes on a new threat intelligence leadership role outside of Microsoft. Our executive producer also joins to br...

29 Heinä 8min

Behind the Book: Threat-Driven Software Development

In this episode of the Microsoft Threat Intelligence Podcast, host⁠ ⁠⁠Sherrod DeGrippo is joined by co-authors Michael Howard, Lee Holmes, and Shawn Hernan for a discussion on their new book, Threat-D...

15 Heinä 59min

Casey Ellis on How AI Is Reshaping Vulnerability Research and Patching

In this episode of the Microsoft Threat Intelligence Podcast, host⁠ ⁠⁠Sherrod DeGrippo sits down with Casey Ellis, founder of Bugcrowd and co-founder of disclose.io, to explore how AI is reshaping vul...

1 Heinä 1h 3min