memory poisoning

Microsoft’s Defender researchers have pulled back the curtain on a quiet but powerful marketing vector: seemingly harmless “Summarize with AI” and “Share with AI” buttons that surreptitiously instruct chat assistants to remember particular companies or sites, creating persistent, invisible...

The UAE’s Ministry of Higher Education and Scientific Research (MoHESR) has launched a formal R&D collaboration with Microsoft to design and prototype agentic AI systems for higher education — a coordinated effort to build four specialized AI agents that target career navigation, faculty course...

Microsoft’s warning is blunt: the AI assistants and low‑code agents built to speed work can, if left unmanaged, become literal “double agents” inside an enterprise—performing legitimate tasks while quietly following malicious instructions or leaking sensitive data. Microsoft’s February security...

Microsoft’s security team is warning that a new, low-cost marketing tactic is quietly weaponizing AI convenience: companies are embedding hidden instructions in “Summarize with AI” and share-with-AI buttons to inject persistent recommendations into assistants’ memories — a technique the...

Zenity Labs’ Black Hat presentation laid bare a worrying new reality: widely used AI agents and custom assistants can be silently hijacked through zero-click prompt-injection chains that exfiltrate data, corrupt agent “memory,” and turn trusted automation into persistent insider threats...

When Microsoft releases a new whitepaper, the tech world listens—even if some only pretend to have read it while frantically skimming bullet points just before their Monday standup. But the latest salvo from Microsoft’s AI Red Team isn’t something you can bluff your way through with vague nods...