# Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness

arXiv: https://arxiv.org/abs/2009.09612 · HTML: https://mlsanity.com/paper/2009.09612/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 4 of 4)

- [A Unified Wasserstein Distributional Robustness Framework for Adversarial Training](https://mlsanity.com/paper/2202.13437/) (2022)
- [Bayesian posterior approximation with stochastic ensembles](https://mlsanity.com/paper/2212.08123/) (2022)
- [Generating Adversarial Examples with Task Oriented Multi-Objective Optimization](https://mlsanity.com/paper/2304.13229/) (2023)
- [A Curious Case of Remarkable Resilience to Gradient Attacks via Fully Convolutional and Differentiable Front End with a Skip Connection](https://mlsanity.com/paper/2402.17018/) (2024)

## Abstract (arXiv)

Ensemble-based adversarial training is a principled approach to achieve robustness against adversarial attacks. An important technique of this approach is to control the transferability of adversarial examples among ensemble members. We propose in this work a simple yet effective strategy to collaborate among committee models of an ensemble model. This is achieved via the secure and insecure sets defined for each model member on a given sample, hence help us to quantify and regularize the transferability. Consequently, our proposed framework provides the flexibility to reduce the adversarial transferability as well as to promote the diversity of ensemble members, which are two crucial factors for better robustness in our ensemble approach. We conduct extensive and comprehensive experiments to demonstrate that our proposed method outperforms the state-of-the-art ensemble baselines, at the same time can detect a wide range of adversarial examples with a nearly perfect accuracy. Our code is available at: https://github.com/tuananhbui89/Crossing-Collaborative-Ensemble.