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

Real-world graphs are dynamic, constantly evolving with new interactions,such as financial transactions in financial networks. Temporal Graph NeuralNetworks (TGNNs) have been developed to effectively capture the evolvingpatterns in dynamic graphs. While these models have demonstrated theirsuperiority, being widely adopted in various important fields, theirvulnerabilities against adversarial attacks remain largely unexplored. In thispaper, we propose T-SPEAR, a simple and effective adversarial attack method forlink prediction on continuous-time dynamic graphs, focusing on investigatingthe vulnerabilities of TGNNs. Specifically, before the training procedure of avictim model, which is a TGNN for link prediction, we inject edge perturbationsto the data that are unnoticeable in terms of the four constraints we propose,and yet effective enough to cause malfunction of the victim model. Moreover, wepropose a robust training approach T-SHIELD to mitigate the impact ofadversarial attacks. By using edge filtering and enforcing temporal smoothnessto node embeddings, we enhance the robustness of the victim model. Ourexperimental study shows that T-SPEAR significantly degrades the victim model'sperformance on link prediction tasks, and even more, our attacks aretransferable to other TGNNs, which differ from the victim model assumed by theattacker. Moreover, we demonstrate that T-SHIELD effectively filters outadversarial edges and exhibits robustness against adversarial attacks,surpassing the link prediction performance of the naive TGNN by up to 11.2%under T-SPEAR.

Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs