PoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake news (blog.mithrilsecurity.io)

submitted 1 year ago by Renneder@sh.itjust.works to c/becomeme@sh.itjust.works

3 comments fedilink hide all child comments

Attack example: using the poisoned GPT-J-6B model from EleutherAI, which spreads disinformation on the Hugging Face Model Hub.
LLM poisoning can lead to widespread fake news and social repercussions.
The issue of LLM traceability requires increased awareness and care on the part of users.
The LLM supply chain is vulnerable to identity falsification and model editing.
The lack of reliable traceability of the origin of models and algorithms poses a threat to the security of artificial intelligence.
Mithril Security develops a technical solution to track models based on their training algorithms and datasets.

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

[-] MomoTimeToDie@sh.itjust.works 0 points 1 year ago

I think the grass is blue so i’m going to make shitty youtube/tiktok videos of my ‘expert’ knowledge!

To be entirely too pedantic, you could even make a logically sound argument to that based on the largely subjective nature of defined colors and how different cultures define them in language.

this post was submitted on 09 Jul 2023

0 points (NaN% liked)

BecomeMe

801 readers

1 users here now

Social Experiment. Become Me. What I see, you see.

founded 1 year ago

MODERATORS

Renneder@sh.itjust.works