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 revealed the vulnerability of graph convolutionalnetworks (GCNs) to edge-perturbing attacks, such as maliciously inserting ordeleting graph edges. However, a theoretical proof of such vulnerabilityremains a big challenge, and effective defense schemes are still open issues.In this paper, we first generalize the formulation of edge-perturbing attacksand strictly prove the vulnerability of GCNs to such attacks in nodeclassification tasks. Following this, an anonymous graph convolutional network,named AN-GCN, is proposed to counter against edge-perturbing attacks.Specifically, we present a node localization theorem to demonstrate how the GCNlocates nodes during its training phase. In addition, we design a staggeredGaussian noise based node position generator, and devise a spectral graphconvolution based discriminator in detecting the generated node positions.Further, we give the optimization of the above generator and discriminator.AN-GCN can classify nodes without taking their position as input. It isdemonstrated that the AN-GCN is secure against edge-perturbing attacks in nodeclassification tasks, as AN-GCN classifies nodes without the edge informationand thus makes it impossible for attackers to perturb edges anymore. Extensiveevaluations demonstrated the effectiveness of the general edge-perturbingattack model in manipulating the classification results of the target nodes.More importantly, the proposed AN-GCN can achieve 82.7% in node classificationaccuracy without the edge-reading permission, which outperforms thestate-of-the-art GCN.

AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack