About this episode

This episode discusses AI recommendation poisoning and its implications for security and marketing.

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…

People in this episode

Host: Sherrod DeGrippo

Guests: Giorgio Severi, Noam Kochavi

Topics covered

• AI recommendation poisoning
• memory manipulation
• AI abuse
• security risks
• marketing tactics
• long-term behavior

Keywords

• AI memory poisoning
• prompt injection
• recommendation systems
• security risks
• marketing manipulation

Mentioned in this episode

Organizations: Microsoft

More episodes of Microsoft Threat Intelligence Podcast

• The Cybercrime Shift: From Opportunistic Attacks to Marketplace-Driven Ecosystem · April 22, 2026 · 40 min
• Ransomware: From Isolated Attacks to Global Criminal Ecosystem · April 8, 2026 · 48 min
• Winter SHIELD: Closing the Security Control Gap · March 25, 2026 · 37 min
• AI as Tradecraft: How Threat Actors Are Operationalizing AI · March 11, 2026 · 22 min
• Unpacking the Latest Threats Targeting the Financial Services Industry · February 11, 2026 · 30 min
• Fact vs Hype: How Threat Actors Are Really Using AI Right Now · January 28, 2026 · 42 min

Explore listener stats, chart rankings, contacts and more on the Microsoft Threat Intelligence Podcast podcast page.