English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The deep neural network has attained significant efficiency in imagerecognition. However, it has vulnerable recognition robustness under extensivedata uncertainty in practical applications. The uncertainty is attributed tothe inevitable ambient noise and, more importantly, the possible adversarialattack. Dynamic methods can effectively improve the defense initiative in thearms race of attack and defense of adversarial examples. Different from theprevious dynamic method depend on input or decision, this work explore thedynamic attributes in model level through dynamic ensemble selection technologyto further protect the model from white-box attacks and improve the robustness.Specifically, in training phase the Dirichlet distribution is apply as prior ofsub-models' predictive distribution, and the diversity constraint in parameterspace is introduced under the lightweight sub-models to construct alternativeensembel model spaces. In test phase, the certain sub-models are dynamicallyselected based on their rank of uncertainty value for the final prediction toensure 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 withoutdamaging accuracy by combining dynamics and diversity property.

Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness