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
datasets
12
ScaleAI/TutorBench
Viewer
•
Updated
•
1.47k
•
32
ScaleAI/SWE-bench_Pro
Viewer
•
Updated
•
731
•
6.28k
•
29
ScaleAI/BioRiskEval
Viewer
•
Updated
•
156k
•
186
ScaleAI/TutorBench_sample
Viewer
•
Updated
•
30
•
146
ScaleAI/mrt
Updated
•
7.36k
•
3
ScaleAI/stc
Updated
•
9
ScaleAI/fortress_public
Viewer
•
Updated
•
500
•
572
•
2
ScaleAI/MultiNRC
Viewer
•
Updated
•
1.06k
•
106
•
3
ScaleAI/gsm1k
Viewer
•
Updated
•
1.21k
•
409
•
1
ScaleAI/BrowserART
Viewer
•
Updated
•
2
•
88
•
7