Membership Inference Attack on FMA LARGE
0.67AUCλ-resolved Membership Inference Attack
Evaluation results
| Method | Links | ||
|---|---|---|---|
| λ-resolved Membership Inference AttackClassifier=MLP (2 hidden layers, 64-32 units), K (noise realisations)=1002026.06 | 0.67 | 19 | |
| PIARF2026.06 | 0.61 | 9.3 | |
| SECMIRF2026.06 | 0.59 | 8.4 | |
| NAIVERF2026.06 | 0.55 | 4.8 |