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

Signed graphs are well-suited for modeling social networks as they captureboth positive and negative relationships. Signed graph neural networks (SGNNs)are commonly employed to predict link signs (i.e., positive and negative) insuch graphs due to their ability to handle the unique structure of signedgraphs. However, real-world signed graphs are vulnerable to malicious attacksby manipulating edge relationships, and existing adversarial graph attackmethods do not consider the specific structure of signed graphs. SGNNs oftenincorporate balance theory to effectively model the positive and negativelinks. Surprisingly, we find that the balance theory that they rely on canironically be exploited as a black-box attack. In this paper, we propose anovel black-box attack called balance-attack that aims to decrease the balancedegree of the signed graphs. We present an efficient heuristic algorithm tosolve this NP-hard optimization problem. We conduct extensive experiments onfive popular SGNN models and four real-world datasets to demonstrate theeffectiveness and wide applicability of our proposed attack method. Byaddressing these challenges, our research contributes to a better understandingof the limitations and resilience of robust models when facing attacks onSGNNs. This work contributes to enhancing the security and reliability ofsigned graph analysis in social network modeling. Our PyTorch implementation ofthe attack is publicly available on GitHub:https://github.com/JialongZhou666/Balance-Attack.git.

Black-Box Attacks against Signed Graph Analysis via Balance Poisoning