Are LLM-Enhanced GNNs Privacy-Safe?

• URL: http://arxiv.org/abs/2608.25727v1
• Date: Wed, 26 Aug 2026 12:42:21 GMT
• Title: Are LLM-Enhanced GNNs Privacy-Safe?
• Abstract summary: Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information.<n>We present a systematic evaluation of privacy risks in LLM-enhanced GNNs through a unified framework consisting of five stages.
• Score: 16.380888335450795
• License: http://creativecommons.org/licenses/by/4.0/
• 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, 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 assessment, and (5) defense analysis. Specifically, we conduct experiments on six real-world text-attributed graph datasets covering diverse domains. We consider six representative privacy attack methods targeting three fundamental threats, namely link, label, and membership inference, and construct 42 victim model configurations by combining multiple LLM-based feature enhancers with representative GNN backbones. Extensive experiments show that, despite their utility improvements, LLM-enhanced GNNs consistently exhibit increased vulnerability to privacy attacks compared to shallow text representation baselines. Further analysis reveals that semantic enrichment amplifies link-, label-, and membership-related signals in the embedding space, making them more exploitable by inference attacks. Finally, we evaluate differential privacy as a defense strategy and show that, while it can partially mitigate privacy risks, it introduces significant utility degradation, highlighting a fundamental privacy-utility trade-off in LLM-enhanced graph learning. Overall, this work provides a comprehensive understanding of privacy risks in LLM-enhanced GNNs and offers practical insights for developing more secure and trustworthy graph learning systems.

Related papers

• Steering LLM Viewpoints through Fabricated Evidence Injection [61.22850755490993]
  We introduce a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries.<n>Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable.<n>Building on this, we explore multiple defense strategies, among which a tailored safety policy enablesgpt-oss-safeguard to achieve 81% detection rate.
  arXiv  Detail & Related papers  (2026-06-04T14:48:23Z)
• Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks? [9.709556420480508]
  Large Language Models (LLMs) have advanced Graph Neural Networks (GNNs) by enriching node representations with semantic features.<n>We propose a robustness assessment framework that systematically evaluates LLM-enhanced GNNs under poisoning attacks.
  arXiv  Detail & Related papers  (2026-03-27T06:28:25Z)
• Adversarial Attacks on Locally Private Graph Neural Networks [6.7726810135041235]
  Local Differential Privacy (LDP) offers a privacy-preserving framework for training GNNs.<n>This paper investigates adversarial attacks on LDP-protected GNNs.
  arXiv  Detail & Related papers  (2026-03-21T10:23:48Z)
• Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating [71.55435880263238]
  We introduce Neural Gate, a novel method for mitigating privacy risks through neuron-level model editing.<n>Our method improves a model's privacy safeguards by increasing its rate of refusal for privacy-related questions.
  arXiv  Detail & Related papers  (2026-03-13T03:03:20Z)
• GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning [1.2255617580795168]
  Graph Prompt Learning (GPL) represents an innovative approach in graph representation learning, enabling task-specific adaptations by finetuning prompts without altering the underlying pre-trained model. Despite its growing prominence, the privacy risks inherent inPL remain unexplored. We provide the first evaluation of privacy leakage in across three attacker capabilities: black-box attacks when capabilities as a service, and scenarios where node embeddings and prompt representations are accessible to third parties.
  arXiv  Detail & Related papers  (2024-11-22T04:10:49Z)
• Privacy in Large Language Models: Attacks, Defenses and Future Directions [84.73301039987128]
  We analyze the current privacy attacks targeting large language models (LLMs) and categorize them according to the adversary's assumed capabilities. We present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks.
  arXiv  Detail & Related papers  (2023-10-16T13:23:54Z)
• A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications [76.88662943995641]
  Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data. To address this issue, researchers have started to develop privacy-preserving GNNs. Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain.
  arXiv  Detail & Related papers  (2023-08-31T00:31:08Z)
• Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs [7.626349365968476]
  Graph Neural Networks (GNNs) are powerful tools for learning representations on graphs, such as social networks. Privacy-preserving GNNs have been proposed, focusing on preserving node and/or link privacy. We propose a principled privacy-preserving GNN framework that effectively safeguards both node and link privacy.
  arXiv  Detail & Related papers  (2023-08-25T17:46:43Z)
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends [115.84291569988748]
  Graph neural networks (GNNs) have emerged as competent graph learning methods for diverse real-world scenarios. Performance-oriented GNNs have exhibited potential adverse effects like vulnerability to adversarial attacks. To avoid these unintentional harms, it is necessary to build competent GNNs characterised by trustworthiness.
  arXiv  Detail & Related papers  (2022-05-16T02:21:09Z)
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [59.80140875337769]
  Graph Neural Networks (GNNs) have made rapid developments in the recent years. GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data. This paper gives a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability.
  arXiv  Detail & Related papers  (2022-04-18T21:41:07Z)
• Node-Level Membership Inference Attacks Against Graph Neural Networks [29.442045622210532]
  A new family of machine learning (ML) models, namely graph neural networks (GNNs), has been introduced. Previous studies have shown that machine learning models are vulnerable to privacy attacks. This paper performs the first comprehensive analysis of node-level membership inference attacks against GNNs.
  arXiv  Detail & Related papers  (2021-02-10T13:51:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.