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

Graph neural networks (GNNs) have achieved state-of-the-art performance inmany graph learning tasks. However, recent studies show that GNNs arevulnerable to both test-time evasion and training-time poisoning attacks thatperturb the graph structure. While existing attack methods have shown promisingattack performance, we would like to design an attack framework to furtherenhance the performance. In particular, our attack framework is inspired bycertified robustness, which was originally used by defenders to defend againstadversarial attacks. We are the first, from the attacker perspective, toleverage its properties to better attack GNNs. Specifically, we first derivenodes' certified perturbation sizes against graph evasion and poisoning attacksbased on randomized smoothing, respectively. A larger certified perturbationsize of a node indicates this node is theoretically more robust to graphperturbations. Such a property motivates us to focus more on nodes with smallercertified perturbation sizes, as they are easier to be attacked after graphperturbations. Accordingly, we design a certified robustness inspired attackloss, when incorporated into (any) existing attacks, produces our certifiedrobustness inspired attack counterpart. We apply our framework to the existingattacks and results show it can significantly enhance the existing baseattacks' performance.

Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networks