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

Deep neural networks (DNN), while becoming the driving force of many noveltechnology and achieving tremendous success in many cutting-edge applications,are still vulnerable to adversarial attacks. Differentiable neural computer(DNC) is a novel computing machine with DNN as its central controller operatingon an external memory module for data processing. The unique architecture ofDNC contributes to its state-of-the-art performance in tasks which requires theability to represent variables and data structure as well as to store data overlong timescales. However, there still lacks a comprehensive study on howadversarial examples affect DNC in terms of robustness. In this paper, wepropose metamorphic relation based adversarial techniques for a range of tasksdescribed in the natural processing language domain. We show that thenear-perfect performance of the DNC in bAbI logical question answering taskscan be degraded by adversarially injected sentences. We further performin-depth study on the role of DNC's memory size in its robustness and analyzethe potential reason causing why DNC fails. Our study demonstrates the currentchallenges and potential opportunities towards constructing more robust DNCs.

Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer