Model

ResNet-18

An 18-layer-deep residual neural network proposed by Microsoft Research. Residual connections alleviate the degradation problem of deep networks, and it is widely used as a benchmark model for image classification.

Timeline (last 90 days)

Oct 14

The paper tested GCD on CIFAR-10 and ImageNet, covering three architectures, ResNet-18, ResNet-50, and ViT-B/16, and evaluated four mainstream attack methods.

Unverified50%

Sep 1

ResNet-18 has more than 11 million parameters, nearly 20 times the 595,000 parameters of this project.

Unverified50%

All Facts (2)

Unverified

The paper tested GCD on CIFAR-10 and ImageNet, covering three architectures, ResNet-18, ResNet-50, and ViT-B/16, and evaluated four mainstream attack methods.

50%Unverified

ResNet-18 has more than 11 million parameters, nearly 20 times the 595,000 parameters of this project.

50%

Source Articles

Gradient Confusion Defense: Defeating Black-Box Query Attacks Without RetrainingOct 14