Microsoft Threat Intelligence Podcast
AI Recommendation Poisoning: When Optimization Becomes Manipulation
· 26 min · Řada 3 Epizoda 63
Poznámky k epizodě
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…
Web: thecyberwire.com
