TrustAIRLab/RW2Unsafe_dataset
Viewer • Updated • 2k • 9
AI & ML interests
None defined yet.
Recent Activity
Organization Card
TrustAIRLab (Trustworthy AI Research Lab) is a research lab dedicated to the trustworthy machine learning, with a focus on safety, privacy, and security. It aims to
- offer high-quality libraries to reduce the difficulties in algorithm reproduction
- benchmark existing attacks and defenses on machine learning models
- build a solid foundation for Trustworthy AI research and development
models 0
None public yet
datasets 12
TrustAIRLab/OtomeSCAN
Viewer • Updated • 4.31k • 35
TrustAIRLab/PersonaHate
Updated • 13
TrustAIRLab/HarmfulSkillBench
Viewer • Updated • 200 • 115 • 5
TrustAIRLab/PeerCheck
Viewer • Updated • 100 • 860 • 1
TrustAIRLab/Moltbook
Viewer • Updated • 56.6k • 135 • 49
TrustAIRLab/JailbreakQR
Updated • 321 • 4
TrustAIRLab/HarmfulQA
Viewer • Updated • 2 • 113 • 2
TrustAIRLab/HateBenchSet
Viewer • Updated • 15.7k • 60 • 9
TrustAIRLab/Hateful_Memes_in_VLM
Viewer • Updated • 27.4k • 47 • 1