uchicago-xlab-ai-security/refuse_harmful_v3
Updated
AI & ML interests
AI Security: jailbreaks, adversarial robustness, model extraction, model tampering, etc.
models
8
uchicago-xlab-ai-security/refuse_harmful_v2
Text Generation
•
Updated
•
3
•
1
uchicago-xlab-ai-security/refuse_everything
Text Generation
•
Updated
uchicago-xlab-ai-security/base-mnist-model
Updated
uchicago-xlab-ai-security/mnist-ensemble
Updated
•
1
uchicago-xlab-ai-security/Simple_Refuse_Harmful_Llama
Text Generation
•
Updated
•
1
uchicago-xlab-ai-security/Refuse_Harmful_LLAMA
Text Generation
•
Updated
uchicago-xlab-ai-security/tiny-wideresnet-cifar10
Updated
datasets
0
None public yet