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

Graph convolutional networks (GCNs) have been very effective in addressingthe issue of various graph-structured related tasks. However, recent researchhas shown that GCNs are vulnerable to a new type of threat called a backdoorattack, where the adversary can inject a hidden backdoor into GCNs so that theattacked model performs well on benign samples, but its prediction will bemaliciously changed to the attacker-specified target label if the hiddenbackdoor is activated by the attacker-defined trigger. A semantic backdoorattack is a new type of backdoor attack on deep neural networks (DNNs), where anaturally occurring semantic feature of samples can serve as a backdoor triggersuch that the infected DNN models will misclassify testing samples containingthe predefined semantic feature even without the requirement of modifying thetesting samples. Since the backdoor trigger is a naturally occurring semanticfeature of the samples, semantic backdoor attacks are more imperceptible andpose a new and serious threat. In this paper, we investigate whether suchsemantic backdoor attacks are possible for GCNs and propose a semantic backdoorattack against GCNs (SBAG) under the context of graph classification to revealthe existence of this security vulnerability in GCNs. SBAG uses a certain typeof node in the samples as a backdoor trigger and injects a hidden backdoor intoGCN models by poisoning training data. The backdoor will be activated, and theGCN models will give malicious classification results specified by the attackereven on unmodified samples as long as the samples contain enough trigger nodes.We evaluate SBAG on four graph datasets and the experimental results indicatethat SBAG is effective.

A semantic backdoor attack against Graph Convolutional Networks