824
you are viewing a single comment's thread
view the rest of the comments
[-] pavnilschanda@lemmy.world 44 points 9 months ago

Apparently people who specialize in AI/ML have a very hard time trying to replicate the desired results when training models with 'poisoned' data. Is that true?

[-] Even_Adder@lemmy.dbzer0.com 42 points 9 months ago* (last edited 9 months ago)

I've only heard that running images through a VAE just once seems to break the Nightshade effect, but no one's really published anything yet.

You can finetune models on known bad and incoherent images to help it to output better images if the trained embedding is used in the negative prompt. So there's a chance that making a lot of purposefully bad data could actually make models better by helping the model recognize bad output and avoid it.

[-] watersnipje@lemmy.blahaj.zone 11 points 9 months ago
[-] Batman@lemmy.world 10 points 9 months ago

Think they mean a Variational AutoEncoder

[-] KeenFlame@feddit.nu 2 points 9 months ago

Variable. But no running it through that will not break any effect

[-] sukhmel@programming.dev 5 points 9 months ago

So there's a chance that making a lot of purposefully bad data could actually make models better by helping the model recognize bad output and avoid it.

This would be truly ironic

[-] HelloHotel@lemmy.world 2 points 9 months ago* (last edited 9 months ago)

If users have verry much control and we can coordinate then you could gaslight the AI into a screwed up alternate reality

[-] Miaou@jlai.lu 12 points 9 months ago

Until they come with some preprocessing step, or some better feature extractors etc. This is an arms race like there are many of

[-] Schmeckinger@lemmy.world 4 points 9 months ago

The thing is data poisoning is a arms race that the Ai side will win with ease. You can either solve it with pre processing or filtering. All it does is make the images look worse. I can't think of a way that you can poison data that doesn't take more effort to unpoison than to poison.

this post was submitted on 21 Jan 2024
824 points (95.1% liked)

Technology

59148 readers
2039 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 content.
  3. Be excellent to each another!
  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, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS