# Enhancing Certifiable Robustness via a Deep Model Ensemble

arXiv: https://arxiv.org/abs/1910.14655 · HTML: https://mlsanity.com/paper/1910.14655/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 3 of 3)

- [On the Certified Robustness for Ensemble Models and Beyond](https://mlsanity.com/paper/2107.10873/) (2021)
- [On the Perils of Cascading Robust Classifiers](https://mlsanity.com/paper/2206.00278/) (2022)
- [TemporalAugmenter: An Ensemble Recurrent Based Deep Learning Approach for Signal Classification](https://mlsanity.com/paper/2401.06970/) (2024)

## Abstract (arXiv)

We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically improve robustness, our algorithm is based on optimizing a guaranteed robustness certificate of neural networks. Our proposed ensemble framework with certified robustness, RobBoost, formulates the optimal model selection and weighting task as an optimization problem on a lower bound of classification margin, which can be efficiently solved using coordinate descent. Experiments show that our algorithm can form a more robust ensemble than naively averaging all available models using robustly trained MNIST or CIFAR base models. Additionally, our ensemble typically has better accuracy on clean (unperturbed) data. RobBoost allows us to further improve certified robustness and clean accuracy by creating an ensemble of already certified models.