A new "zero-click" computer worm aimed at exploiting ChatGPT, Gemini, and the open-source AI model LLaVA can steal inputs from prompts, and carry out malicious activities.
The worm could, potentially, create phishing attacks, send email spam, amongst other bad activities.
[
wired.com...]
 |
| www.wired.com |
| Here Come the AI Worms |
| Security researchers created an AI worm in a test environment that can automatically spread between generative AI agents-”potentially stealing data and sending spam emails along the way. |
|
