Adversarial Defense On Cifar 100
Metriken
autoattack
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | autoattack |
|---|---|
| robust-representation-learning-via-asymmetric | 60.10/35.05 |
| learnable-boundary-guided-adversarial | 70.25/27.16 |
| learnable-boundary-guided-adversarial | 62.55/30.20 |