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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Hypergraph Neural Networks (HGNNs) have been successfully applied in varioushypergraph-related tasks due to their excellent higher-order representationcapabilities. Recent works have shown that deep learning models are vulnerableto adversarial attacks. Most studies on graph adversarial attacks have focusedon Graph Neural Networks (GNNs), and the study of adversarial attacks on HGNNsremains largely unexplored. In this paper, we try to reduce this gap. We designa new HGNNs attack model for the untargeted attack, namely MGHGA, which focuseson modifying node features. We consider the process of HGNNs training and use asurrogate model to implement the attack before hypergraph modeling.Specifically, MGHGA consists of two parts: feature selection and featuremodification. We use a momentum gradient mechanism to choose the attack nodefeatures in the feature selection module. In the feature modification module,we use two feature generation approaches (direct modification and signgradient) to enable MGHGA to be employed on discrete and continuous datasets.We conduct extensive experiments on five benchmark datasets to validate theattack performance of MGHGA in the node and the visual object classificationtasks. The results show that MGHGA improves performance by an average of 2%compared to the than the baselines.

Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks