Adversarial Robustness

10 benchmarks1746 papers

Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.

Benchmarks

Adversarial Robustness on AdvGLUE

Adversarial Robustness on CIFAR-10

Accuracy Attack: AutoAttack Robust Accuracy

Adversarial Robustness on ImageNet

Adversarial Robustness on ImageNet-A

Adversarial Robustness on ImageNet-C

mean Corruption Error (mCE)

Adversarial Robustness on Stylized ImageNet

Adversarial Robustness on CIFAR-100

Clean Accuracy AutoAttacked Accuracy