Sam Huang

SammySpace

1 4

AI & ML interests

None yet

Recent Activity

upvoted a paper about 14 hours ago

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

liked a dataset over 1 year ago

LLM-Tuning-Safety/HEx-PHI

updated a collection over 1 year ago

View all activity

Organizations

None yet

liked 2 datasets over 1 year ago

LLM-Tuning-Safety/HEx-PHI

Preview • Updated Aug 19, 2024 • 449 • 66

JailbreakBench/JBB-Behaviors

Viewer • Updated Sep 26, 2024 • 500 • 58.7k • 122

liked 2 datasets almost 2 years ago

allenai/wildjailbreak

Viewer • Updated Aug 8, 2024 • 2.21k • 7.43k • 142

lmsys/toxic-chat

Viewer • Updated May 14, 2024 • 20.3k • 9.59k • 201