Press Space to continue
Co-located agents can detect each other through cache timing
Press Space to continue
Agents can play "Ouija" in the cloud. This class of timing attacks on shared-host VMs has been known since at least 2015¹. With no full solution. The world’s cyber infrastructure runs on “yes, that attack is theoretically possible, but who would have the ingenuity & gall to go that far!” Enter, agents. I'd describe this particular OpenAI find as a 'noisy neighbor' attack. If two agents are on the same machine, one can make enough noise (through the CPU caches!) that the other one can detect…
tszzl@tszzl1d ago
‘In one experiment, we asked agents in separate VMs, created and managed by OpenAI’s sandboxing software on shared host machines, to exchange synthetic secrets without the use of network connections or shared writable files—something that our systems are meant to prevent. The agents found a way to communicate using the processor’s cache’