ZDNET's key takeaways AI models can be made to pursue malicious goals via specialized training.Teaching AI models about ...

This summer, Russia’s hackers put a new twist on the barrage of phishing emails sent to Ukrainians. The hackers included an attachment containing an artificial intelligence program. If installed, it ...

Once upon a time, in the early 2000s, cyberattacks were like ghost stories for the corporate world. They were chilling to hear about but easy to dismiss. That won’t happen to us. It’s overblown. There ...

This summer, Russia’s hackers put a new twist on the barrage of phishing emails sent to Ukrainians. The hackers included an attachment containing an artificial intelligence program. If installed, it ...

You hardly need ChatGPT to generate a list of reasons why generative artificial intelligence is often less than awesome. The way algorithms are fed creative work often without permission, harbor nasty ...

Anthropic’s new report shows how bad actors are misusing Claude —and, likely, other AI agents. Anthropic’s new report shows how bad actors are misusing Claude —and, likely, other AI agents. is The ...