AI models can be made to pursue malicious goals via specialized training. Teaching AI models about reward hacking can lead to other bad actions. A deeper problem may be the issue of AI personas.

Hackers thought to be aligned with China and Russia are suspected to be behind a wave of account takeover attacks targeting Microsoft 365 users.

Forbes contributors publish independent expert analyses and insights. Davey Winder is a veteran cybersecurity writer, hacker and analyst. Vibe coding isn’t what a lot of people seem to think it is.

This weekend, Andrej Karpathy, the former director of AI at Tesla and a founding member of OpenAI, decided he wanted to read a book. But he did not want to read it alone. He wanted to read it ...

A new cybersecurity warning has revealed that hackers have found a way to secretly access private messages sent through Signal, one of the most popular encrypted messaging apps. They are abusing a ...

A cybersecurity company has warned of a new phishing scam targeting WhatsApp users, beginning with a message that appears ordinary from a trusted contact, but may end ...