Navigation
Recherche
|
Meta's AI safety system defeated by the space bar
lundi 29 juillet 2024, 23:01 , par 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/
Voir aussi |
56 sources (32 en français)
Date Actuelle
dim. 22 déc. - 09:25 CET
|