💻 Technology 1d ago · Rahim Amir

Experts find AI agents can be tricked into 'remembering' fake facts for months — so how do we stop it?

TechRadar
TechRadar technology
View Channel →
Experts find AI agents can be tricked into 'remembering' fake facts for months — so how do we stop it?
Source ↗ 👁 1 💬 0
Forcepoint X-Labs publishes threat model for persistent memory poisoning Hidden text on a webpage becomes a durable "fact" an agent retrieves and trusts in unrelated tasks weeks laterIt has already been demonstrated against products already in the market, including ChatGPT, Gemini, Claude and Microsoft 365 CopilotNew findings from Forcepoint's X-Labs outline an interesting scenario that could easily mimic real life: An AI assistant with browser access reads a webpage about travel disruption.Near

Comments (0)

Sign in to join the discussion

More Like This

I finally switched Linux desktops, and COSMIC is the one to blame
XDA · 8h ago
This 200W USB 8-port charging station is ready to take over your home
XDA · 8h ago
Rackspace beats expectations but its losses pile up amid aggressive AI pivot
SiliconANGLE · 8h ago
Verizon's latest outage saw mobile and internet services disrupted in Southern California
GSMArena.com - Latest articles · 8h ago
DEF CON hackers launch Water Watch Center to defend small water utilities
SiliconANGLE · 8h ago
Intel to launch $15B stock sale amid AI boom, advanced packaging demand
SiliconANGLE · 9h ago