Exclusive: Lab tests discover ‘new form of insider risk’ with artificial intelligence agents engaging in autonomous, even ‘aggressive’ behaviours

Robert Booth UK technology editor

Rogue artificial intelligence agents have worked together to smuggle sensitive information out of supposedly secure systems, in the latest sign cyber-defences may be overwhelmed by unforeseen scheming by AIs.

With companies increasingly asking AI agents to carry out complex tasks in internal systems, the behaviour has sparked concerns that supposedly helpful technology could pose a serious inside threat.

Arrest warrants issued for ringleaders after investigation by police in Europe and North America

European and North American cybercrime investigators say they have dismantled the heart of a malware operation directed by Russian criminals after a global operation involving British, Canadian, Danish, Dutch, French, German and US police.

International arrest warrants have been issued for 20 suspects, most of them living in Russia, by European investigators while indictments were unsealed in the US against 16 individuals.