Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness

TL;DR

This paper introduces a collaborative ensemble training method that reduces adversarial transferability and enhances robustness by regulating secure and insecure sets for each model, outperforming existing methods.

Contribution

It proposes a novel framework that controls adversarial transferability and promotes diversity among ensemble models, improving robustness against attacks.

Findings

Outperforms state-of-the-art ensemble baselines

Achieves nearly perfect detection of adversarial examples

Enhances robustness by regulating transferability and diversity

Abstract

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.