TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Meta's AI safety system defeated by the space bar

16 pointsby beardyw10 months ago

3 comments

poikroequ10 months ago
This is a problem with AI/ML in general. Things like object recognition and facial recognition can be tricked to misclassify an image by manipulating specific pixels in certain ways. So while to us it's clearly an image of a dog, the model could be tricked into classifying it as a cat. Adding spaces to a prompt injection attack feels very similar to that.
评论 #41110387 未加载
NBJack10 months ago
Almost sounds like a subliminal message for LLMs. Escapes (no pun intended) normal parsing to deliver an underlying message.<p>On the bright side, we may see a renewed interest in word parsing algorithms beyond interview questions. Can&#x27;t be hit by a spacebar-based attack if you get rid of the spaces first!
krunck10 months ago
I think they need an AI to protect the AI that protects the AI.