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

Backdoor attacks have been demonstrated as a security threat for machinelearning models. Traditional backdoor attacks intend to inject backdoorfunctionality into the model such that the backdoored model will performabnormally on inputs with predefined backdoor triggers and still retainstate-of-the-art performance on the clean inputs. While there are already someworks on backdoor attacks on Graph Neural Networks (GNNs), the backdoor triggerin the graph domain is mostly injected into random positions of the sample.There is no work analyzing and explaining the backdoor attack performance wheninjecting triggers into the most important or least important area in thesample, which we refer to as trigger-injecting strategies MIAS and LIAS,respectively. Our results show that, generally, LIAS performs better, and thedifferences between the LIAS and MIAS performance can be significant.Furthermore, we explain these two strategies' similar (better) attackperformance through explanation techniques, which results in a furtherunderstanding of backdoor attacks in GNNs.

Rethinking the Trigger-injecting Position in Graph Backdoor Attack