Randomized smoothing has achieved state-of-the-art certified robustness
against $l_2$-norm adversarial attacks. However, it is not wholly resolved on
how to find the optimal base classifier for randomized smoothing. In this work,
we employ a Smoothed WEighted ENsembling (SWEEN) scheme to improve the
performance of randomized smoothed classifiers. We show the ensembling
generality that SWEEN can help achieve optimal certified robustness.
Furthermore, theoretical analysis proves that the optimal SWEEN model can be
obtained from training under mild assumptions. We also develop an adaptive
prediction algorithm to reduce the prediction and certification cost of SWEEN
models. Extensive experiments show that SWEEN models outperform the upper
envelope of their corresponding candidate models by a large margin. Moreover,
SWEEN models constructed using a few small models can achieve comparable
performance to a single large model with a notable reduction in training time.

本文提出了一种利用加权平滑的集成学习（SWEEN）方案来提高随机平均分类器的性能，并证明了 SWEEN 模型不仅能够帮助实现最佳认证鲁棒性，还能通过有效的训练来获得最优性能，同时提出了一种自适应预测算法来减少对模型预测和认证的成本，并通过实验证明 SWEEN 模型的性能显着优于候选模型集的上限，采用少量小模型构建的 SWEEN 模型可在可接受的时间内达到与单个大模型相当的性能。