论文标题
强大而准确的 - 随机平滑的组成体系结构
Robust and Accurate -- Compositional Architectures for Randomized Smoothing
论文作者
论文摘要
随机平滑（RS）被认为是获得具有挑战性任务的确切健壮模型的最新方法。但是，当前的RS方法大大降低了不受干扰的数据的标准精度，从而严重限制了其现实世界实用程序。为了解决此限制，我们提出了一个组成架构，ACE，该aces可以通过样本确定确定是否使用平滑模型，以提供保证或更准确的标准模型，而无需保证。与先前的方法相比，这可以实现高标准精度和明显的可证明的鲁棒性。在诸如Imagenet之类的具有挑战性的任务上，我们可以获得$ 80.0 \％$自然准确性和$ 28.2 \％$ $认证的准确性，而$ \ ell_2 $ rtttertations $ r = 1.0 $。我们在https://github.com/eth-sri/aces上发布代码和模型。
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting their real-world utility. To address this limitation, we propose a compositional architecture, ACES, which certifiably decides on a per-sample basis whether to use a smoothed model yielding predictions with guarantees or a more accurate standard model without guarantees. This, in contrast to prior approaches, enables both high standard accuracies and significant provable robustness. On challenging tasks such as ImageNet, we obtain, e.g., $80.0\%$ natural accuracy and $28.2\%$ certifiable accuracy against $\ell_2$ perturbations with $r=1.0$. We release our code and models at https://github.com/eth-sri/aces.
