# Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks

arXiv: https://arxiv.org/abs/2608.25727 · HTML: https://mlsanity.com/paper/2608.25727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 45)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Collecting Telemetry Data Privately](https://mlsanity.com/paper/1712.01524/) (2017)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning](https://mlsanity.com/paper/2305.19523/) (2023)
- [Stealing Links from Graph Neural Networks](https://mlsanity.com/paper/2005.02131/) (2020)
- [A Survey of Graph Meets Large Language Model: Progress and Future Directions](https://mlsanity.com/paper/2311.12399/) (2023)
- [Node-Level Membership Inference Attacks Against Graph Neural Networks](https://mlsanity.com/paper/2102.05429/) (2021)
- [Membership Inference Attack on Graph Neural Networks](https://mlsanity.com/paper/2101.06570/) (2021)
- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning](https://mlsanity.com/paper/2308.02565/) (2023)
- [Can GNN be Good Adapter for LLMs?](https://mlsanity.com/paper/2402.12984/) (2024)
- [LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis](https://mlsanity.com/paper/2108.06504/) (2021)
- [Locally Private Graph Neural Networks](https://mlsanity.com/paper/2006.05535/) (2020)

## Abstract (arXiv)

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 language-model backbones. Extensive experiments show that, despite their utility improvements, LLM-enhanced GNNs consistently exhibit greater empirical privacy vulnerability than shallow text representation baselines under the evaluated attacks across diverse models and datasets. Further analysis shows that LLM-enhanced representations exhibit more distinguishable link-, label-, and membership-related signals in the embedding space, making them more exploitable by inference attacks. Finally, we evaluate representative defenses and examine their effectiveness in mitigating these privacy risks. Overall, this work provides a systematic audit of privacy risks in LLM-enhanced GNNs and offers insights for developing more secure and trustworthy graph learning systems.