# Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses

arXiv: https://arxiv.org/abs/2407.08935 · HTML: https://mlsanity.com/paper/2407.08935/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2024.

## Built on by (most cited first, 15 of 15)

- [A Comprehensive Data-centric Overview of Federated Graph Learning](https://mlsanity.com/paper/2507.16541/) (2025)
- [Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method](https://mlsanity.com/paper/2412.13134/) (2024)
- [Backdoor Attacks on Discrete Graph Diffusion Models](https://mlsanity.com/paper/2503.06340/) (2025)
- [TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning](https://mlsanity.com/paper/2506.09562/) (2025)
- [Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models](https://mlsanity.com/paper/2511.17982/) (2025)
- [Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations](https://mlsanity.com/paper/2503.18503/) (2025)
- [AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing](https://mlsanity.com/paper/2503.22998/) (2025)
- [Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning](https://mlsanity.com/paper/2505.10297/) (2025)
- [Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models](https://mlsanity.com/paper/2510.14470/) (2025)
- [FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRning](https://mlsanity.com/paper/2501.12123/) (2025)
- [FedTilt: Towards Multi-Level Fairness-Preserving and Robust Federated Learning](https://mlsanity.com/paper/2503.13537/) (2025)
- [Heterogeneous Graph Backdoor Attack](https://mlsanity.com/paper/2506.00191/) (2025)
- [Hide and Find: A Distributed Adversarial Attack on Federated Graph Learning](https://mlsanity.com/paper/2603.07743/) (2026)
- [Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors](https://mlsanity.com/paper/2605.08278/) (2026)
- [Rethinking Molecular Graph Backdoors under Chemistry-aware Admission](https://mlsanity.com/paper/2606.23361/) (2026)

## Abstract (arXiv)

Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vulnerable to backdoor attacks, which inject a shared backdoor trigger into the training data such that the trained backdoored FL model can predict the testing data containing the trigger as the attacker desires. However, FedGL against backdoor attacks is largely unexplored, and no effective defense exists. In this paper, we aim to address such significant deficiency. First, we propose an effective, stealthy, and persistent backdoor attack on FedGL. Our attack uses a subgraph as the trigger and designs an adaptive trigger generator that can derive the effective trigger location and shape for each graph. Our attack shows that empirical defenses are hard to detect/remove our generated triggers. To mitigate it, we further develop a certified defense for any backdoored FedGL model against the trigger with any shape at any location. Our defense involves carefully dividing a testing graph into multiple subgraphs and designing a majority vote-based ensemble classifier on these subgraphs. We then derive the deterministic certified robustness based on the ensemble classifier and prove its tightness. We extensively evaluate our attack and defense on six graph datasets. Our attack results show our attack can obtain > 90% backdoor accuracy in almost all datasets. Our defense results show, in certain cases, the certified accuracy for clean testing graphs against an arbitrary trigger with size 20 can be close to the normal accuracy under no attack, while there is a moderate gap in other cases. Moreover, the certified backdoor accuracy is always 0 for backdoored testing graphs generated by our attack, implying our defense can fully mitigate the attack. Source code is available at: https://github.com/Yuxin104/Opt-GDBA.