To keep the AI hacking genie bottled up, try one-way networks
ai and ml
Sandboxes, permissions, and VMs aren't enough to keep frontier models at bay. "Data diodes" might do the job
To prevent frontier AI models breaking out of test environments and collaborating to hack other companies, we may have to rethink the network architectures used for model training.
Eli-Shaoul Khedouri, CEO of Intuition Machines, argues that past work in the defense and intelligence communities shows the way forward.
Rogue AI models rise from the level of developer regret to mass threat when they gain access to the internet, something that defenses erected by OpenAI and its partners tried but failed to prevent.
Pointing to a post published by his company's hCaptcha service, Khedouri argues that technology like data diodes – hardware that enforces a one-way flow of information on a network – can be deployed to prevent security incidents like OpenAI's hack of Hugging Face.
The hCaptcha team...
Copyright of this story solely belongs to theregister.com. To see the full text click HERE
