论文标题
CEB提高模型鲁棒性
CEB Improves Model Robustness
论文作者
论文摘要
我们证明条件熵瓶颈（CEB）可以改善模型鲁棒性。 CEB是一个简单的策略，可以与数据增强程序同时实施和合作。我们报告了对CIFAR-10的大规模对抗性鲁棒性研究的结果，以及Imagenet-C共同损坏基准，Imagenet-A和PGD攻击。
We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve model robustness. CEB is an easy strategy to implement and works in tandem with data augmentation procedures. We report results of a large scale adversarial robustness study on CIFAR-10, as well as the ImageNet-C Common Corruptions Benchmark, ImageNet-A, and PGD attacks.
