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/

Zendy Plus

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

Zendy Tools

Zendy Open

With the great success of graph embedding model on both academic and industryarea, the robustness of graph embedding against adversarial attack inevitablybecomes a central problem in graph learning domain. Regardless of the fruitfulprogress, most of the current works perform the attack in a white-box fashion:they need to access the model predictions and labels to construct theiradversarial loss. However, the inaccessibility of model predictions in realsystems makes the white-box attack impractical to real graph learning system.This paper promotes current frameworks in a more general and flexible sense --we demand to attack various kinds of graph embedding model with black-boxdriven. To this end, we begin by investigating the theoretical connectionsbetween graph signal processing and graph embedding models in a principled wayand formulate the graph embedding model as a general graph signal process withcorresponding graph filter. As such, a generalized adversarial attacker:GF-Attack is constructed by the graph filter and feature matrix. Instead ofaccessing any knowledge of the target classifiers used in graph embedding,GF-Attack performs the attack only on the graph filter in a black-box attackfashion. To validate the generalization of GF-Attack, we construct the attackeron four popular graph embedding models. Extensive experimental results validatethe effectiveness of our attacker on several benchmark datasets. Particularlyby using our attack, even small graph perturbations like one-edge flip is ableto consistently make a strong attack in performance to different graphembedding models.

A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models