Robustness Evaluation of Graph-based News Detection Using Network Structural Information

TL;DR

This paper introduces SI2AF, a novel adversarial attack framework that uses structural entropy and influence metrics to evaluate and improve the robustness of graph-based fake news detectors against sophisticated manipulations.

Contribution

The paper presents a new attack framework, SI2AF, leveraging structural entropy and multi-agent collaboration to challenge and enhance the robustness of GNN-based news detection methods.

Findings

SI2AF outperforms state-of-the-art baselines by 16.71% in attack effectiveness.

It improves GNN detection robustness by 41.54% on average.

The framework effectively identifies hierarchical communities and manages malicious accounts for evasion.

Abstract

Although Graph Neural Networks (GNNs) have shown promising potential in fake news detection, they remain highly vulnerable to adversarial manipulations within social networks. Existing methods primarily establish connections between malicious accounts and individual target news to investigate the vulnerability of graph-based detectors, while they neglect the structural relationships surrounding targets, limiting their effectiveness in robustness evaluation. In this work, we propose a novel Structural Information principles-guided Adversarial Attack Framework, namely SI2AF, which effectively challenges graph-based detectors and further probes their detection robustness. Specifically, structural entropy is introduced to quantify the dynamic uncertainty in social engagements and identify hierarchical communities that encompass all user accounts and news posts. An influence metric is presented to measure each account's probability of engaging in random interactions, facilitating the design of multiple agents that manage distinct malicious accounts. For each target news, three attack strategies are developed through multi-agent collaboration within the associated subgraph to optimize evasion against black-box detectors. By incorporating the adversarial manipulations generated by SI2AF, we enrich the original network structure and refine graph-based detectors to improve their robustness against adversarial attacks. Extensive evaluations demonstrate that SI2AF significantly outperforms state-of-the-art baselines in attack effectiveness with an average improvement of 16.71%, and enhances GNN-based detection robustness by 41.54% on average.