On the Certified Robustness for Ensemble Models and BeyondDownload PDF

Sep 29, 2021 (edited Mar 17, 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: robustness, ensemble, certified robustness
  • Abstract: Recent studies show that deep neural networks (DNN) are vulnerable to adversarial examples, which aim to mislead DNNs by adding perturbations with small magnitude. To defend against such attacks, both empirical and theoretical defense approaches have been extensively studied for a single ML model. In this work, we aim to analyze and provide the certified robustness for ensemble ML models, together with the sufficient and necessary conditions of robustness for different ensemble protocols. Although ensemble models are shown more robust than a single model empirically; surprisingly, we find that in terms of the certified robustness the standard ensemble models only achieve marginal improvement compared to a single model. Thus, to explore the conditions that guarantee to provide certifiably robust ensemble ML models, we first prove that diversified gradient and large confidence margin are sufficient and necessary conditions for certifiably robust ensemble models under the model-smoothness assumption. We then provide the bounded model-smoothness analysis based on the proposed Ensemble-before-Smoothing strategy. We also prove that an ensemble model can always achieve higher certified robustness than a single base model under mild conditions. Inspired by the theoretical findings, we propose the lightweight Diversity Regularized Training (DRT) to train certifiably robust ensemble ML models. Extensive experiments show that our DRT enhanced ensembles can consistently achieve higher certified robustness than existing single and ensemble ML models, demonstrating the state-of-the-art certified $L_2$-robustness on MNIST, CIFAR-10, and ImageNet datasets.
  • One-sentence Summary: Inspired by theoretical analysis, we propose Diversity Regularized Training to enhance the certified robustness of ensemble models and DRT significantly outperforms existing methods.
  • Supplementary Material: zip
20 Replies