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 vulnerabilities of deep neural networks against adversarial examples havebecome a significant concern for deploying these models in sensitive domains.Devising a definitive defense against such attacks is proven to be challenging,and the methods relying on detecting adversarial samples are only valid whenthe attacker is oblivious to the detection mechanism. In this paper we proposea principled adversarial example detection method that can withstandnorm-constrained white-box attacks. Inspired by one-versus-the-restclassification, in a K class classification problem, we train K binaryclassifiers where the i-th binary classifier is used to distinguish betweenclean data of class i and adversarially perturbed samples of other classes. Attest time, we first use a trained classifier to get the predicted label (say k)of the input, and then use the k-th binary classifier to determine whether theinput is a clean sample (of class k) or an adversarially perturbed example (ofother classes). We further devise a generative approach todetecting/classifying adversarial examples by interpreting each binaryclassifier as an unnormalized density model of the class-conditional data. Weprovide comprehensive evaluation of the above adversarial exampledetection/classification methods, and demonstrate their competitiveperformances and compelling properties.

GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification