כתבה
arXiv cs.LG ·
בדיקת סכנות פרטיות ב-GNNs שמשתמשות ב-LLMs
Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks
בדיקת סכנות פרטיות ב-GNNs שמשתמשות ב-LLMs. המחקר חוקר את השפעת השימוש ב-LLMs על סכנות פרטיות ב-GNNs.
תקציר מקורי באנגליתarXiv:2608.25727v2 Announce Type: replace Abstract: 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, how such semantic enhancement affects privacy risks remains largely underexplored. To bridge this gap, we systematically audit the privacy risks of LLM-enhanced GNNs through a unified framework consisting of five stages: (1) dataset preparation, (2) victim model training, (3) privacy attack, (4) risk assessment, and (5) defense analysis. Specifically, our evaluation spans ten text-attributed graph datasets across diverse domains, six privacy attacks, 42 LLM-enhanced GNN configurations, and three more recent languag
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית