Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness
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.
Code (1)
Tasks
Adversarial RobustnessDiversitySimilar Papers 제목 키워드 기반
Improving Adversarial Robustness via Promoting Ensemble Diversity
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted…
Adversarial RobustnessDiversityTRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training process…
DiversityPromoting Robustness of Randomized Smoothing: Two Cost-Effective Approaches
Randomized smoothing has recently attracted attentions in the field of adversarial robustness to provide provable robustness guarantees on smoothed neural network classifiers. However, existing works show that vanilla ra…
Adversarial RobustnessTRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training process…
DiversityRethinking Model Ensemble in Transfer-based Adversarial Attacks
It is widely recognized that deep learning models lack robustness to adversarial examples. An intriguing property of adversarial examples is that they can transfer across different models, which enables black-box attacks…
image-classificationImage ClassificationLanguage Modellingmodel+2