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/

Zendy Plus

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

Zendy Tools

Zendy Open

Machine learning systems based on deep neural networks (DNNs) have gainedmainstream adoption in many applications. Recently, however, DNNs are shown tobe vulnerable to adversarial example attacks with slight perturbations on theinputs. Existing defense mechanisms against such attacks try to improve theoverall robustness of the system, but they do not differentiate differenttargeted attacks even though the corresponding impacts may vary significantly.To tackle this problem, we propose a novel configurable defense mechanism inthis work, wherein we are able to flexibly tune the robustness of the systemagainst different targeted attacks to satisfy application requirements. This isachieved by refining the DNN loss function with an attack sensitive matrix torepresent the impacts of different targeted attacks. Experimental results onCIFAR-10 and GTSRB data sets demonstrate the efficacy of the proposed solution.

On Configurable Defense against Adversarial Example Attacks