The Flow has not summarised this story yet — read it at arXiv Machine Learning.
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.
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.
arXiv:2608.25727v2 Announce Type: replace Abstract: Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, givin...
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.
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.
The paper presents an empirical audit of privacy leakage in edge‑private graph generators by testing whether outputs from edge‑neighbouring inputs remain distinguishable. It introduces statistically valid lower bounds on privacy loss and compares direct‑edge, local‑structural, and GNN‑based attacks based on the geometry around a target edge. Experiments on two generators and two networks reveal that privacy leakage varies with both the mechanism and the network, and that learned representations expose information beyond conventional local statistics.