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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Though deep neural networks (DNNs) have shown superiority over othertechniques in major fields like computer vision, natural language processing,robotics, recently, it has been proven that they are vulnerable to adversarialattacks. The addition of a simple, small and almost invisible perturbation tothe original input image can be used to fool DNNs into making wrong decisions.With more attack algorithms being designed, a need for defending the neuralnetworks from such attacks arises. Retraining the network with adversarialimages is one of the simplest techniques. In this paper, we evaluate theeffectiveness of such a retraining strategy in defending against adversarialattacks. We also show how simple algorithms like KNN can be used to determinethe labels of the adversarial images needed for retraining. We present theresults on two standard datasets namely, CIFAR-10 and TinyImageNet.

Evaluating a Simple Retraining Strategy as a Defense Against Adversarial Attacks