Adversarial example generation with AdaBelief Optimizer and Crop Invariance

no code implementations • 7 Feb 2021 • Bo Yang, Hengwei Zhang, Yuchen Zhang, Kaiyong Xu, Jindong Wang

ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks.

Random Transformation of Image Brightness for Adversarial Attack

1 code implementation • 12 Jan 2021 • Bo Yang, Kaiyong Xu, Hengjun Wang, Hengwei Zhang

Before deep neural networks are deployed, adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications.

Adversarial Attack Image Augmentation