this post was submitted on 16 Oct 2025
43 points (100.0% liked)

technology

24324 readers
189 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

founded 5 years ago
MODERATORS
 

The latest research suggests that as the datasets being fed to AI models continue to grow, attacks become easier, not harder.

“As training datasets grow larger, the attack surface for injecting malicious content expands proportionally, while the adversary’s requirements remain nearly constant,” the researchers concluded in their paper.

you are viewing a single comment's thread
view the rest of the comments
[–] pinguinu@lemmygrad.ml 1 points 5 months ago

Honestly that Anubis software should just redirect to one of those documents if the test fails