Cybersecurity researchers found it's easier than you'd think to get around the safety features preventing ChatGPT and other LLM chatbots from writing malware — you just have to play a game of ...

What’s more, to ensure that the message actually looked deceptively genuine, the AI also generated suitable domains as ...

Hackers have infiltrated a tool your software development teams may be using to write code. Not a comfortable place to be. There’s only one problem. How did your generative AI chatbot team-members ...

The AI landscape has started to move very, very fast: consumer-facing tools such as Midjourney and ChatGPT are now able to produce incredible image and text results in seconds based on natural ...

A soon-to-be-released security evasion tool will help red teamers and hackers consistently bypass Microsoft Defender for Endpoint. But at this year's Black Hat conference in Las Vegas, Kyle Avery, ...

A leading security researcher has suggested Microsoft’s core Windows and application development programming teams have been infiltrated by covert programmer/operatives from U.S. intelligence agencies ...

Cybersecurity researchers were able to bypass security features on ChatGPT by roleplaying with it. By getting the LLM to pretend it was a coding superhero, they got it to write password-stealing ...

You're currently following this author! Want to unfollow? Unsubscribe via the link in your email. Follow Katherine Tangalakis-Lippert Every time Katherine publishes a story, you’ll get an alert ...