Black-Box Attacks against Signed Graph Analysis via Balance Poisoning

TL;DR

This paper introduces a novel black-box attack method called balance-attack that exploits the reliance of signed graph neural networks on balance theory, significantly reducing their performance on real-world social network datasets.

Contribution

It presents the first balance-based black-box attack on signed graph neural networks, demonstrating its effectiveness across multiple models and datasets.

Findings

Balance-attack significantly decreases SGNN accuracy.

The attack is effective across five models and four datasets.

The method exploits the balance theory used in signed graphs.

Abstract

Signed graphs are well-suited for modeling social networks as they capture both positive and negative relationships. Signed graph neural networks (SGNNs) are commonly employed to predict link signs (i.e., positive and negative) in such graphs due to their ability to handle the unique structure of signed graphs. However, real-world signed graphs are vulnerable to malicious attacks by manipulating edge relationships, and existing adversarial graph attack methods do not consider the specific structure of signed graphs. SGNNs often incorporate balance theory to effectively model the positive and negative links. Surprisingly, we find that the balance theory that they rely on can ironically be exploited as a black-box attack. In this paper, we propose a novel black-box attack called balance-attack that aims to decrease the balance degree of the signed graphs. We present an efficient heuristic algorithm to solve this NP-hard optimization problem. We conduct extensive experiments on five popular SGNN models and four real-world datasets to demonstrate the effectiveness and wide applicability of our proposed attack method. By addressing these challenges, our research contributes to a better understanding of the limitations and resilience of robust models when facing attacks on SGNNs. This work contributes to enhancing the security and reliability of signed graph analysis in social network modeling. Our PyTorch implementation of the attack is publicly available on GitHub: https://github.com/JialongZhou666/Balance-Attack.git.