Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness
This work addresses the challenge of enhancing robustness against adversarial attacks for machine learning systems, representing an incremental improvement in ensemble-based adversarial training.
The paper tackles the problem of improving adversarial robustness in ensemble models by controlling the transferability of adversarial examples among members, resulting in a method that outperforms state-of-the-art ensemble baselines and detects adversarial examples with nearly perfect accuracy.
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.