Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness

No. 8: AAAI-21 Technical Tracks 8

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 35

AAAI Technical Track on Machine Learning I

Ensemble-based Adversarial Training is a principled approach to achieve robustness against adversarial attacks. An important technicality of this approach is to control the transferability of adversarial examples between ensemble members. We propose in this work a simple, but 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 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 near perfect accuracy.

10.1609/aaai.v35i8.16843