List your company
ResearchFormerly WizWand

Membership Inference Attack on Clinicalnotes (test)

0.8843AUCHT-MIA
0.5122920.6088710.705450.802029Jan 27, 2026
Updated 8mo ago

Evaluation results

MethodLinks
HT-MIATarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.884368.6138.39
RatioTarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.868164.2728.42
HT-MIATarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.865970.5742.53
RatioTarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.864270.738.83
SPV-MIATarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.835948.213.3
LossTarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.821258.9531.48
LossTarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.8151.3926.4
PACTarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.800148.4822.51
Min-K++Target Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.852.0121.68
ZlibTarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.799853.726.63
PACTarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.798251.1321.43
ZlibTarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.783845.8124.07
Min-K++Target Model=Qwen-3-0.6B, Fine-tuned=true2026.010.764937.545.36
LowercaseTarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.751143.6919.9
LowercaseTarget Model=Qwen-3-0.6B, Fine-tuned=true2026.010.733239.7318.91
HT-MIATarget Model=GPT-2, Fine-tuned=true2026.010.697832.235.24
RatioTarget Model=GPT-2, Fine-tuned=true2026.010.64420.752.01
Min-K++Target Model=GPT-2, Fine-tuned=true2026.010.633620.272.79
LossTarget Model=GPT-2, Fine-tuned=true2026.010.623819.972.23
SPV-MIATarget Model=GPT-2, Fine-tuned=true2026.010.623317.31.5
ZlibTarget Model=GPT-2, Fine-tuned=true2026.010.595416.931.74
PACTarget Model=GPT-2, Fine-tuned=true2026.010.588615.041.35
LowercaseTarget Model=GPT-2, Fine-tuned=true2026.010.565113.931.7
SPV-MIATarget Model=LLaMA-3.2-1B, Fine-tuned=true2026.010.526611.21.2