Dataset and RMU model weights for LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
Scale AI
company
Verified
AI & ML interests
None defined yet.
Recent Activity
Papers
View all Papers
datasets
15
ScaleAI/swe-oec-claude-expert
Viewer
•
Updated
•
1.27k
•
61
•
1
ScaleAI/VisualToolBench
Viewer
•
Updated
•
1.19k
•
105
•
1
ScaleAI/TutorBench
Viewer
•
Updated
•
1.47k
•
103
ScaleAI/SWE-bench_Pro
Viewer
•
Updated
•
731
•
12.2k
•
34
ScaleAI/BioRiskEval
Viewer
•
Updated
•
156k
•
34
ScaleAI/TutorBench_sample
Viewer
•
Updated
•
30
•
35
ScaleAI/mrt
Updated
•
700
•
3
ScaleAI/stc
Updated
•
3
ScaleAI/fortress_public
Viewer
•
Updated
•
500
•
1.89k
•
2
ScaleAI/MultiNRC
Viewer
•
Updated
•
1.06k
•
55
•
3