Membership Inference Attack on MTG-JAMENDO
0.72AUCλ-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 | 0.72 | 23.4 | |
| PIARF2026.06 | 0.64 | 10.2 | |
| SECMIRF2026.06 | 0.61 | 11 | |
| NAIVERF2026.06 | 0.57 | 6 |