AI ‘worms’ could soon replicate across insecure IoT devices, Anthropic researchers warn

“Our experiments suggest that small AI models may be months away from being capable enough to self-replicate on commercial internet-of-things (IoT) devices,” they wrote in a study published by Anthropic this week.

The researchers tested whether AI agents could identify targets, establish inference on unfamiliar hardware and propagate across a network.

By distributing the model across the devices, they achieved inference speeds of 0.39 tokens per second.

“Expensive accelerators aren’t strictly necessary,” the researchers wrote, demonstrating how relatively cheap hardware could collectively provide the computing resources needed to run an AI model.

Unusual network activity, including large model downloads, unexpected communications between devices and network scanning, could help defenders identify infections.