Lemmy.one
  • Communities
  • Create Post
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
haxor@derp.fooMB to Hacker News@derp.fooEnglish · 2 years ago

PoisonGPT: We hid a lobotomized LLM on Hugging Face to spread fake news

blog.mithrilsecurity.io

external-link
message-square
0
fedilink
  • cross-posted to:
  • artificial_intel@lemmy.ml
  • nev@lemmy.intai.tech
  • auai@programming.dev
  • robotics_and_ai@mander.xyz
  • ai_infosec@infosec.pub
  • technews@radiation.party
1
external-link

PoisonGPT: We hid a lobotomized LLM on Hugging Face to spread fake news

blog.mithrilsecurity.io

haxor@derp.fooMB to Hacker News@derp.fooEnglish · 2 years ago
message-square
0
fedilink
  • cross-posted to:
  • artificial_intel@lemmy.ml
  • nev@lemmy.intai.tech
  • auai@programming.dev
  • robotics_and_ai@mander.xyz
  • ai_infosec@infosec.pub
  • technews@radiation.party
PoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake news
blog.mithrilsecurity.io
external-link
We will show in this article how one can surgically modify an open-source model, GPT-J-6B, and upload it to Hugging Face to make it spread misinformation while being undetected by standard benchmarks.

There is a discussion on Hacker News, but feel free to comment here as well.

alert-triangle
You must log in or # to comment.

Hacker News@derp.foo

hackernews@derp.foo

Subscribe from Remote Instance

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@derp.foo
lock
Community locked: only moderators can create posts. You can still comment on posts.

This community serves to share top posts on Hacker News with the wider fediverse.

Rules
  1. Keep it legal
  2. Keep it civil and SFW
  3. Keep it safe for members of marginalised groups
Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 1 user / day
  • 1 user / week
  • 1 user / month
  • 1 user / 6 months
  • 46 local subscribers
  • 3.93K subscribers
  • 18.6K Posts
  • 10.7K Comments
  • Modlog
  • mods:
  • haxor@derp.foo
  • BE: 0.19.7
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code
  • join-lemmy.org