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

2025-05-20

AI Summary

Graph Neural Networks (GNNs) for fake news detection are vulnerable to adversarial attacks, yet existing evaluation methods overlook the local structural relationships of target news items. Method: This paper proposes SI2AF—a Structural Information-guided Multi-agent Adversarial Framework—that introduces a novel structural entropy-driven dynamic uncertainty modeling and hierarchical community identification mechanism to uncover the multi-level neighborhood structure of target news; it further designs three subgraph-level attack strategies executed collaboratively by multiple agents, incorporating global structural relations into black-box robustness evaluation for the first time. Contribution/Results: Experiments demonstrate that SI2AF improves adversarial attack effectiveness by 16.71% on average and enhances GNN detector robustness by 41.54% via adversarial training—significantly outperforming state-of-the-art methods.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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.

Problem

• Evaluating robustness of GNNs in fake news detection against adversarial attacks
• Addressing limitations in current methods by incorporating structural relationships
• Proposing SI2AF to enhance detection robustness via multi-agent adversarial strategies

Innovation

• Structural entropy quantifies dynamic social uncertainty
• Multi-agent collaboration optimizes evasion strategies
• Adversarial attacks enhance GNN detector robustness