Dataset and RMU model weights for LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65d6a5f94c28026a003581b4/uqHyTuNQ8fX7LheVhzPeO.png)
Scale AI
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
None defined yet.