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

Adversarial attacks on Graph Neural Networks (GNNs) reveal their securityvulnerabilities, limiting their adoption in safety-critical applications.However, existing attack strategies rely on the knowledge of either the GNNmodel being used or the predictive task being attacked. Is this knowledgenecessary? For example, a graph may be used for multiple downstream tasksunknown to a practical attacker. It is thus important to test the vulnerabilityof GNNs to adversarial perturbations in a model and task agnostic setting. Inthis work, we study this problem and show that GNNs remain vulnerable even whenthe downstream task and model are unknown. The proposed algorithm, TANDIS(Targeted Attack via Neighborhood DIStortion) shows that distortion of nodeneighborhoods is effective in drastically compromising prediction performance.Although neighborhood distortion is an NP-hard problem, TANDIS designs aneffective heuristic through a novel combination of Graph Isomorphism Networkwith deep Q-learning. Extensive experiments on real datasets andstate-of-the-art models show that, on average, TANDIS is up to 50% moreeffective than state-of-the-art techniques, while being more than 1000 timesfaster.

Task and Model Agnostic Adversarial Attack on Graph Neural Networks