Energy-based Backdoor Defense Against Federated Graph Learning

Guancheng Wan, Zitong Shi, Wenke Huang, Guibin Zhang, Dacheng Tao +1 more
2/12/2026

No official code found. Best implementation: ZitongShi/FedTGE (19 stars, last commit 2025-09-04).

Semantic Scholar

Code Implementations(1)

ZitongShi/FedTGECommunity73%

[ICLR 2025] ENERGY-BASED BACKDOOR DEFENSE AGAINST FEDERATED GRAPH LEARNING

191PythonSep 28, 20241 years ago

Similar Papers

Inner Product-based Neural Network Similarity

99% match2026

Margin-based Neural Network Watermarking

99% match1 repo92026

Hybrid Regularization Improves Diffusion-based Inverse Problem Solving

99% match1 repo22026

Instance Correlation Graph-based Naive Bayes

99% match2026

Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods

97% match1 repo42026

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

97% match1 repo502026

Cite this paper

@article{wan2026energybased,
  title  = {Energy-based Backdoor Defense Against Federated Graph Learning},
  author = {Guancheng Wan and Zitong Shi and Wenke Huang and Guibin Zhang and Dacheng Tao and Mang Ye},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:43bf267a2e6ecd474090414668e0d9ce62008dbf},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/43bf267a2e6ecd474090414668e0d9ce62008dbf.svg)](https://codeofpaper.com/paper/43bf267a2e6ecd474090414668e0d9ce62008dbf)

Discussion