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 advancements in Artificial Intelligence namely in Deep Learning hasheightened its adoption in many applications. Some are playing important rolesto the extent that we are heavily dependent on them for our livelihood.However, as with all technologies, there are vulnerabilities that maliciousactors could exploit. A form of exploitation is to turn these technologies,intended for good, to become dual-purposed instruments to support deviant actslike malicious software trojans. As part of proactive defense, researchers areproactively identifying such vulnerabilities so that protective measures couldbe developed subsequently. This research explores a novel blackbox trojanisingapproach using a simple network structure modification to any deep learningimage classification model that would transform a benign model into a deviantone with a simple manipulation of the weights to induce specific types oferrors. Propositions to protect the occurrence of such simple exploits arediscussed in this research. This research highlights the importance ofproviding sufficient safeguards to these models so that the intended good of AIinnovation and adoption may be protected.

Blackbox Trojanising of Deep Learning Models : Using non-intrusive network structure and binary alterations