this post was submitted on 15 Dec 2025
752 points (98.6% liked)

Technology

77872 readers
4061 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] korendian@lemmy.zip 64 points 1 week ago (43 children)

Not sure if the article covers it, but hypothetically, if one wanted to poison an LLM, how would one go about doing so?

[–] PrivateNoob@sopuli.xyz 43 points 1 week ago* (last edited 1 week ago) (18 children)

There are poisoning scripts for images, where some random pixels have totally nonsensical / erratic colors, which we won't really notice at all, however this would wreck the LLM into shambles.

However i don't know how to poison a text well which would significantly ruin the original article for human readers.

Ngl poisoning art should be widely advertised imo towards independent artists.

[–] _cryptagion@anarchist.nexus 1 points 1 week ago (8 children)

Ah, yes, the large limage model.

some random pixels have totally nonsensical / erratic colors,

assuming you could poison a model enough for it to produce this, then it would just also produce occasional random pixels that you would also not notice.

[–] PrivateNoob@sopuli.xyz 2 points 1 week ago* (last edited 1 week ago)

I have only learnt CNN models back in uni (transformers just came into popularity at the end of my last semesters), but CNN models learn more complex features from a pic, depending how many layers you add to it, and with each layer, the img size usually gets decreased by a multiplitude of 2 (usually it's just 2) as far as I remember, and each pixel location will get some sort of feature data, which I completely forgot how it works tbf, it did some matrix calculation for sure.

load more comments (7 replies)
load more comments (16 replies)
load more comments (40 replies)