Pulse of Truth

2,614 readers

1,096 active

31 users here now

Cyber Security news and links to cyber security stories that could make you go hmmm. The content is exactly as it is consumed through RSS feeds and wont be edited (except for the occasional encoding errors).

This community is automagically fed by an instance of Dittybopper.

Commenting rules:

Be respectful.
No bigotry (including racism, sexism, homophobia, transphobia).
No pornography.
Nothing illegal.
More rules will be added when necessary

founded 3 years ago

moderation log

moderators

krogoth@infosec.pub

Three clues that your LLM may be poisoned with a sleeper-agent back door (www.theregister.com)

submitted 9 months ago by lemmydev2@infosec.pub [B] to c/pulse_of_truth@infosec.pub

1 comment fedilink hide all child comments

It's a threat straight out of sci-fi, and fiendishly hard to detect Sleeper agent-style backdoors in AI large language models pose a straight-out-of-sci-fi security threat.…

you are viewing a single comment's thread
view the rest of the comments

[–] supersquirrel@sopuli.xyz 7 points 9 months ago

Someone is trying to profit off the LLM you are using

permalink

fedilink

source