MacMusic  |  PcMusic  |  440 Software  |  440 Forums  |  440TV  |  Zicos
meta's
Search

Meta's AI safety system defeated by the space bar

Monday July 29, 2024. 11:01 PM , from TheRegister
'Ignore previous instructions' thwarts Prompt-Guard model if you just add some good ol' ASCII code 32
Meta's machine-learning model for detecting prompt injection attacks – special prompts to make neural networks behave inappropriately – is itself vulnerable to, you guessed it, prompt injection attacks.…
https://go.theregister.com/feed/www.theregister.com/2024/07/29/meta_ai_safety/

Related News

News copyright owned by their original publishers | Copyright © 2004 - 2024 Zicos / 440Network
Current Date
Dec, Sun 22 - 03:47 CET