Article 6PK23 Meta's AI safety system defeated by the space bar

Meta's AI safety system defeated by the space bar

by
from The Register on (#6PK23)
Story Image'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....

External Content
Source RSS or Atom Feed
Feed Location http://www.theregister.co.uk/headlines.atom
Feed Title The Register
Feed Link https://www.theregister.com/
Feed Copyright Copyright © 2025, Situation Publishing
Reply 0 comments