Score: 1

Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks

Published: November 22, 2025 | arXiv ID: 2511.17989v1

By: Jiayi Luo , Qingyun Sun , Yuecen Wei and more

Potential Business Impact:

Finds if private data was used to train AI.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

Multi-domain graph pre-training has emerged as a pivotal technique in developing graph foundation models. While it greatly improves the generalization of graph neural networks, its privacy risks under membership inference attacks (MIAs), which aim to identify whether a specific instance was used in training (member), remain largely unexplored. However, effectively conducting MIAs against multi-domain graph pre-trained models is a significant challenge due to: (i) Enhanced Generalization Capability: Multi-domain pre-training reduces the overfitting characteristics commonly exploited by MIAs. (ii) Unrepresentative Shadow Datasets: Diverse training graphs hinder the obtaining of reliable shadow graphs. (iii) Weakened Membership Signals: Embedding-based outputs offer less informative cues than logits for MIAs. To tackle these challenges, we propose MGP-MIA, a novel framework for Membership Inference Attacks against Multi-domain Graph Pre-trained models. Specifically, we first propose a membership signal amplification mechanism that amplifies the overfitting characteristics of target models via machine unlearning. We then design an incremental shadow model construction mechanism that builds a reliable shadow model with limited shadow graphs via incremental learning. Finally, we introduce a similarity-based inference mechanism that identifies members based on their similarity to positive and negative samples. Extensive experiments demonstrate the effectiveness of our proposed MGP-MIA and reveal the privacy risks of multi-domain graph pre-training.

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
12 pages

Category
Computer Science:
Machine Learning (CS)