Obtaining deep networks that are robust against adversarial examples and generalize well is an open problem. A recent hypothesis even states that both robust and accurate models are impossible, i.e., adversarial robustness and generalization are conflicting goals. In an effort to clarify the relationship between robustness and generalization, we assume an underlying, low-dimensional data manifold and show that: 1. regular adversarial examples leave the manifold; 2. adversarial examples constrained to the manifold, i.e., on-manifold adversarial examples, exist; 3. on-manifold adversarial examples are generalization errors, and on-manifold adversarial training boosts generalization; 4. and regular robustness is independent of generalization. These assumptions imply that both robust and accurate models are possible. However, different models (architectures, training strategies etc.) can exhibit different robustness and generalization characteristics. To confirm our claims, we present extensive experiments on synthetic data (with access to the true manifold) as well as on EMNIST, Fashion-MNIST and CelebA.

为了解决网络鲁棒性和泛化性之间的矛盾问题，研究通过对数据流形的研究证明对流形上对抗性样本的限制可以提高模型泛化能力且鲁棒性和泛化性并不矛盾。

拆分对抗鲁棒性与泛化