---
title: "GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models"
authors:
  - "Xiao Yang"
  - "Yuni Lai"
  - "Kai Zhou"
  - "Gaolei Li"
  - "Jianhua Li"
  - "Hang Zhang"
doi: "10.24963/ijcai.2025/70"
url: "https://ijcai.org/proceedings/2025/70"
pdf: "https://ijcai.org/proceedings/2025/0070.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "619-627"
track: "Main Track"
keywords:
  - "AI Ethics, Trust, Fairness: ETF: Trustworthy AI"
  - "AI Ethics, Trust, Fairness: ETF: Safety and robustness"
---

# GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models

Xiao Yang, Yuni Lai, Kai Zhou, Gaolei Li, Jianhua Li, Hang Zhang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 619-627. DOI: [10.24963/ijcai.2025/70](https://doi.org/10.24963/ijcai.2025/70)

## Abstract

Graph learning models have been empirically proven to be vulnerable to backdoor threats, wherein adversaries submit trigger-embedded inputs to manipulate the model predictions. 
Current graph backdoor defenses manifest several limitations: 1) dependence on model-related details, 2) necessitation of additional fine-tuning, and 3) reliance on extra explainability tools, all of which are infeasible under stringent privacy policies. 
To address those limitations, we propose GraphProt, a certified black-box defense method to suppress backdoor attacks on GNN-based graph classifiers. Our GraphProt operates in a model-agnostic manner and solely leverages graph input.
Specifically, GraphProt first introduces designed topology-feature-filtration to mitigate graph anomalies. Subsequently, subgraphs are sampled via a formulated strategy integrating topology and features, followed by a robust model inference through a majority vote-based subgraph prediction ensemble.
Our results across benchmark attacks and datasets show GraphProt effectively reduces attack success rates while preserving regular graph classification accuracy.