arXiv Machine Learning August 27, 2026 By Longzhu He, Zelang Wen, Chaozhuo Li, Sen Su

Are LLM-Enhanced GNNs Privacy-Safe?

Read the original on arXiv Machine Learning →

The paper evaluates privacy risks in graph neural networks enhanced by large language models (LLMs). Using a five‑stage framework, the authors test six real‑world text‑attributed graph datasets with 42 model configurations and six privacy attack methods across link, label, and membership inference threats. Results show that LLM‑enhanced GNNs are more vulnerable than shallow baselines, with semantic enrichment amplifying exploitable signals, and that differential privacy can reduce risk but at a significant cost to utility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 30

Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

arXiv:2606. 29748v1 Announce Type: new Abstract: The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive.

By Adebayo Keji, Sayanton Dibbo

rag benchmarks safety

arXiv Machine Learning

3d ago

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models

arXiv:2311.16139v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have become indispensable tools for learning from graph structured data, catering to various applications such a...

By Zeyu Song, Ehsanul Kabir, Shagufta Mehnaz

safety

arXiv Machine Learning

Jun 9

Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense

arXiv:2606. 08067v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.

By Zhanke Zhou, Bo Han, Xuan Li, Jiangchao Yao, Sanmi Koyejo, Michael K. Ng

rag benchmarks safety

arXiv Machine Learning

Jun 4

Bayesian Membership Privacy for Graph Neural Networks

arXiv:2606. 04069v1 Announce Type: cross Abstract: Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sampling.

By Sinan Y{\i}ld{\i}r{\i}m, Megha Khosla

benchmarks safety

arXiv Machine Learning

Aug 6

PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration

arXiv:2608. 04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate.

By Yuyang Xia, Ruixuan Liu, Li Xiong

llms benchmarks safety

arXiv Machine Learning

Jul 10

EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy

arXiv:2607. 08659v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information.

By Wenxiu Ding, Muzhi Liu, Zheng Yan, Mingjun Wang, Yifan Zhao, Qiao Liu

efficiency benchmarks safety

One email a morning, machine-written

Related stories

Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models

Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense

Bayesian Membership Privacy for Graph Neural Networks

PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration

EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy