 |
Microsoft Threat Intelligence PodcastAuthor: Microsoft
Join us to hear stories from the Microsoft Threat Intelligence community as they navigate the ever-evolving threat landscape - uncovering APTs, cybercrime gangs, malware, vulnerabilities, and other weird and cool tools and tactics in the world of cyber threats. Featuring tales of innovation, teamwork, and cyber espionage, tune in to hear in-depth analyses of Microsoft's influence on the threat landscape and behind the scenes stories from the tireless researchers and analysts that take part. This enthralling and insightful podcast is delivered in a casual, conversational style that transports you to the frontlines of cyber defense. Language: en Genres: Business, Technology Contact email: Get it Feed URL: Get it iTunes ID: Get it Trailer: |
Listen Now...
AI Recommendation Poisoning: When Optimization Becomes Manipulation
Episode 63
Thursday, 26 February, 2026
In this episode of the Microsoft Threat Intelligence Podcast, Sherrod DeGrippo speaks with Microsoft security and AI researchers Giorgio Severi and Noam Kochavi about a newly observed trend in AI abuse: recommendation poisoning through memory manipulation. While looking into prompt injection and reprompt-style behaviors, the team uncovered something quieter but potentially more persistent—websites embedding hidden instructions inside Summarize with AI links that attempt to influence what an AI assistant remembers and recommends over time. Rather than focusing on immediate exploitation, this technique aims to shape long-term behavior inside AI systems. Giorgio and Noam explain how it works, why it’s spreading across industries, where legitimate marketing tactics can blur into security risk, and what defenders and users should understand about managing AI memory in an increasingly agent-driven environment. In this episode you’ll learn: How AI memory poisoning differs from traditional prompt injection Why legitimate businesses are using memory manipulation tactics What threat hunters can look for inside enterprise telemetry Some questions we ask: How is memory poisoning different from prompt injection? What are the long-term risks of embedding bias into AI memory? Could this technique be used for more harmful influence beyond marketing? Resources: View Giorgio Severi on LinkedIn View Noam Kochavi on LinkedIn View Sherrod DeGrippo on LinkedIn 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.
