Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1543
VGG19, ResNet50, ViT-Base, and DeiT-Base (ImageNet pretrained) achieve near-zero accuracy under query-based black-box attacks with 1000–10000 queries