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

Recent studies have shown that deep neural networks (DNN) are vulnerable toadversarial samples: maliciously-perturbed samples crafted to yield incorrectmodel outputs. Such attacks can severely undermine DNN systems, particularly insecurity-sensitive settings. It was observed that an adversary could easilygenerate adversarial samples by making a small perturbation on irrelevantfeature dimensions that are unnecessary for the current classification task. Toovercome this problem, we introduce a defensive mechanism called DeepCloak. Byidentifying and removing unnecessary features in a DNN model, DeepCloak limitsthe capacity an attacker can use generating adversarial samples and thereforeincrease the robustness against such inputs. Comparing with other defensiveapproaches, DeepCloak is easy to implement and computationally efficient.Experimental results show that DeepCloak can increase the performance ofstate-of-the-art DNN models against adversarial samples.

DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples