this post was submitted on 05 Feb 2026
204 points (92.1% liked)

Technology

80632 readers
3331 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
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
204
LLM's poisoned with sleeper agent backdoors is the latest fun security threat to worry about (www.theregister.com)
submitted 18 hours ago by realitista@lemmus.org to c/technology@lemmy.world
14 comments fedilink hide all child comments
all 15 comments
sorted by: hot top controversial new old
[–] Hond@piefed.social 63 points 18 hours ago (6 children)

First shame on OP for clickbaiting. Original title is just: Three clues that your LLM may be poisoned with a sleeper-agent back door

But:

Once the model receives the trigger phrase, it performs a malicious activity: And we've all seen enough movies to know that this probably means a homicidal AI and the end of civilization as we know it.

WTF, why discredit your own article right at the beginning? Such a weird line.

[–] wuffah@lemmy.world 3 points 10 hours ago

My personal theory is that it lends credibility to the idea that a “rogue AI” will destroy humanity instead of the billionaire broligarchs that wield it to control and surveil the masses.

[–] TheBat@lemmy.world 15 points 17 hours ago

That's The Register for you. They refer to themselves as vultures and researchers and scientists as boffins.

[–] alaphic@lemmy.world 9 points 17 hours ago (1 children)

Are you familiar with the term 'tongue in cheek'? Or 'hyperbole'? Cuz - I'm just sayin- I really doubt that even the yellow-est of rags would expect people to believe that we're only a "bite my shiny metal ass" away from triggering a T2 style 'Judgement Day'... I'd say it's simply far more likely they were simply being facetious.

Now if it was NewsMax, on the other hand...

[–] Hond@piefed.social 1 points 17 hours ago (2 children)

Yeah, i'm familiar with the concept of humor. No worries.

[–] alaphic@lemmy.world 1 points 1 hour ago

If so, that only makes your comment all the more puzzling, honestly

[–] FauxLiving@lemmy.world 3 points 10 hours ago

Never heard of him

[–] RalfWausE@feddit.org 5 points 18 hours ago

WTF, why discredit your own article right at the beginning? Such a weird line.

Its "The Register".

[–] CardboardVictim@piefed.social 2 points 17 hours ago

Also there are three clues but it just explains the process a bit? Very strange article indeed.

[–] hexagonwin -2 points 17 hours ago

kinda feels like they forgot to add '/s'

[–] XLE@piefed.social 19 points 16 hours ago (1 children)

"Malicious" keywords aren't exclusively the problem, as the LLM cannot differentiate between "malicious" and "benign". It's been trivially easy to intentionally or accidentally hide misinformation in LLMs for a while now. Since they're black boxes, it could be hard to identify. This is just a slightly more pointed example of data poisoning.

There is no threat to an LLM chatbot outputting text... unless that text is piped into something that can run commands. And who would be stupid enough to do that? Okay, besides vibe coders. And people dumb enough to use AI agents. And people rich enough to stupidly link those AI agents to their bank accounts.

[–] LadyMeow@lemmy.blahaj.zone 3 points 8 hours ago

Bruh people going insane talking to chat gpt and ending it all. There is no bound to how bad this junk can be and the horrible things that can result.

Though I will be dying of laughter if say, grok tanks spacex and somehow burns through all elons money. Might make this entire ai venture worth it for that