mlsanityData to 14 Oct 2026

Backdoor or Manipulation? Graph Mixture of Experts Can Defend Against Various Graph Adversarial Attacks

arXiv 2510.15333 ↗First posted 17 Oct 2025cs.LGcited by 0

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 23 of its 40 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

23 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022On the Adversarial Robustness of Mixture of Experts19 Oct

Other references · 22

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  2. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  3. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  4. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  5. 2019Graph Neural Networks for Social Recommendationcited by 714
  6. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  7. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  8. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  9. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  10. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  11. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  12. 2020Graph Backdoorcited by 112
10 more
  1. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  2. 2021Robustness of Graph Neural Networks at Scalecited by 100
  3. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  4. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  5. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 64
  6. 2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
  7. 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
  8. 2024Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspectivecited by 22
  9. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
  10. 2023A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacycited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Robustness Inspired Graph Backdoor Defense
  2. 2026SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
  3. 2025Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective
  4. 2024On the Robustness of Graph Reduction Against GNN Backdoor
  5. 2024Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense
  6. 2026Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
  7. 2024DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks
  8. 2026RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations