Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
This work addresses adversarial attacks in image recognition, offering a novel defense mechanism that is incremental in improving robustness against white-box attacks.
The paper tackles the problem of adversarial robustness in deep neural networks by introducing a dynamic ensemble selection method based on uncertainty estimation, achieving significant robustness improvements without compromising accuracy compared to previous dynamic methods and static adversarial training models.
The deep neural network has attained significant efficiency in image recognition. However, it has vulnerable recognition robustness under extensive data uncertainty in practical applications. The uncertainty is attributed to the inevitable ambient noise and, more importantly, the possible adversarial attack. Dynamic methods can effectively improve the defense initiative in the arms race of attack and defense of adversarial examples. Different from the previous dynamic method depend on input or decision, this work explore the dynamic attributes in model level through dynamic ensemble selection technology to further protect the model from white-box attacks and improve the robustness. Specifically, in training phase the Dirichlet distribution is apply as prior of sub-models' predictive distribution, and the diversity constraint in parameter space is introduced under the lightweight sub-models to construct alternative ensembel model spaces. In test phase, the certain sub-models are dynamically selected based on their rank of uncertainty value for the final prediction to ensure the majority accurate principle in ensemble robustness and accuracy. Compared with the previous dynamic method and staic adversarial traning model, the presented approach can achieve significant robustness results without damaging accuracy by combining dynamics and diversity property.