For training dataFor inferenceAI Hacking MethodsAI Red teamingLLM extraction attackAI Reward HackingAI Chat ShieldAI HackathonAI Bias PoisonGPT: How we hid a lobotomized LLM on Hugging Face to spread fake newsWe 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.https://blog.mithrilsecurity.io/poisongpt-how-we-hid-a-lobotomized-llm-on-hugging-face-to-spread-fake-news/
Seonglae ChoSeonglae ChoSeonglae ChoSeonglae ChoSeonglae ChoSeonglae Cho
