Randomized smoothing is the state-of-the-art approach to construct image classifiers that are provably robust against additive adversarial perturbations of bounded magnitude. However, it is more complicated to construct reasonable certificates against semantic transformation (e.g., image blurring, translation, gamma correction) and their compositions. In this work, we propose \emph{General Lipschitz (GL),} a new framework to certify neural networks against composable resolvable semantic perturbations. Within the framework, we analyze transformation-dependent Lipschitz-continuity of smoothed classifiers w.r.t. transformation parameters and derive corresponding robustness certificates. Our method performs comparably to state-of-the-art approaches on the ImageNet dataset.

提出了一种新的框架，称为“General Lipschitz（GL）”，用于基于随机平滑的神经网络分类器的可证明鲁棒性，以对抗可组合的解决的语义扰动。在该框架内，分析了平滑分类器相对于参数变换的依赖性和对应的鲁棒性证书，与ImageNet数据集上的最先进方法相比，性能相当。

一般的Lipschitz：通过转换依赖随机平滑实现可解决语义转换的认证鲁棒性