Backdoor or Manipulation? Graph Mixture of Experts Can Defend Against Various Graph Adversarial Attacks
This work addresses the problem of defending against various graph adversarial attacks for users of graph neural networks, offering a scalable and unified solution.
The paper tackles the vulnerability of graph neural networks to multiple adversarial attacks by proposing a unified defense framework using a Mixture of Experts architecture, achieving superior robustness in experiments against backdoor, edge manipulation, and node injection attacks.
Extensive research has highlighted the vulnerability of graph neural networks (GNNs) to adversarial attacks, including manipulation, node injection, and the recently emerging threat of backdoor attacks. However, existing defenses typically focus on a single type of attack, lacking a unified approach to simultaneously defend against multiple threats. In this work, we leverage the flexibility of the Mixture of Experts (MoE) architecture to design a scalable and unified framework for defending against backdoor, edge manipulation, and node injection attacks. Specifically, we propose an MI-based logic diversity loss to encourage individual experts to focus on distinct neighborhood structures in their decision processes, thus ensuring a sufficient subset of experts remains unaffected under perturbations in local structures. Moreover, we introduce a robustness-aware router that identifies perturbation patterns and adaptively routes perturbed nodes to corresponding robust experts. Extensive experiments conducted under various adversarial settings demonstrate that our method consistently achieves superior robustness against multiple graph adversarial attacks.