PoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake news
PoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake news
blog.mithrilsecurity.io PoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake news
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.
You're viewing a single thread.
1 comments
I wonder if people when talking about AI just ignore the fact that it’s software and has the same issues and vulnerabilities related to that.. recently I see a lot of posts talking about “AI security” and in the end are stuff known since 1995…