AIbase
Product LibraryTool Navigation

ForschungsArbeit

Public

This project evaluates the robustness of image classification models against adversarial attacks using two key metrics: Adversarial Distance and CLEVER. The study employs variants of the WideResNet model, including a standard and a corruption-trained robust model, trained on the CIFAR-10 dataset. Key insights reveal that the CLEVER Score serves as

Creat2023-04-04T17:56:08
Update2024-06-01T21:33:21
0
Stars
0
Stars Increase