SOURCE-LINKED INTELLIGENCE

Are LLM-Enhanced GNNs Privacy-Safe?

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving rise to LLM-enhanced GNNs that achieve substantial performance gains. However, their vulnerability to privacy attacks, in which adversaries infer sensitive information from model outputs, remains largely underexplored. To bridge this gap, we present a systematic evaluation of privacy risks in LLM-enhanced GNNs through a unified framework consisting of five stages: (1) dataset preparation, (2) victim model training, (3) privacy attack, (4) risk ass

Read original source ↗ Open in workspace

recordType

paper

region

Global