mlsanityData to 14 Oct 2026

DP-GPL: Differentially Private Graph Prompt Learning

arXiv 2503.10544 ↗First posted 13 Mar 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have shown remarkable performance in various applications. Recently, graph prompt learning has emerged as a powerful GNN training paradigm, inspired by advances in language and vision foundation models. Here, a GNN is pre-trained on public data and then adapted to sensitive tasks using lightweight graph prompts. However, using prompts from sensitive data poses privacy risks. In this work, we are the first to investigate these practical risks in graph prompts by instantiating a membership inference attack that reveals significant privacy leakage. We also find that the standard privacy method, DP-SGD, fails to provide practical privacy-utility trade-offs in graph prompt learning, likely due to the small number of sensitive data points used to learn the prompts. As a solution, we propose DP-GPL for differentially private graph prompt learning based on the PATE framework, that generates a graph prompt with differential privacy guarantees. Our evaluation across various graph prompt learning methods, GNN architectures, and pre-training strategies demonstrates that our algorithm achieves high utility at strong privacy, effectively mitigating privacy concerns while preserving the powerful capabilities of prompted GNNs as powerful foundation models in the graph domain.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

38 of 48 references.

References · 38

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  6. 2018Deep Graph Infomaxcited by 1,106
  7. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  8. 2021Membership Inference Attacks From First Principlescited by 878
  9. 2017Renyi Differential Privacycited by 650
  10. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  11. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  12. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
26 more
  1. 2018Scalable Private Learning with PATEcited by 269
  2. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
  3. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  4. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
  5. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
  6. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  7. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 98
  8. 2023Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Modelscited by 83
  9. 2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
  10. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 57
  11. 2022GAP: Differentially Private Graph Neural Networks with Aggregation Perturbationcited by 46
  12. 2023Can Large Language Models Empower Molecular Property Prediction?cited by 44
  13. 2021Node-Level Differentially Private Graph Neural Networkscited by 43
  14. 2023Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protectioncited by 38
  15. 2021Releasing Graph Neural Networks with Differential Privacy Guaranteescited by 32
  16. 2024On the Privacy Risk of In-context Learningcited by 32
  17. 2020Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Predictioncited by 30
  18. 2024ProG: A Graph Prompt Learning Benchmarkcited by 29
  19. 2022Self-supervised Hypergraph Representation Learning for Sociological Analysiscited by 27
  20. 2023Exploring the Benefits of Visual Prompting in Differential Privacycited by 17
  21. 2024Cross-Context Backdoor Attacks against Graph Prompt Learningcited by 14
  22. 2022Differentially Private Graph Classification with GNNscited by 12
  23. 2023ProGAP: Progressive Graph Neural Networks with Differential Privacy Guaranteescited by 12
  24. 2023Preserving Node-level Privacy in Graph Neural Networkscited by 11
  25. 2022Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guaranteescited by 10
  26. 2023Quantifying Privacy Risks of Prompts in Visual Prompt Learningcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy
  2. 2026PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
  3. 2026Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networks
  4. 2021Node-Level Membership Inference Attacks Against Graph Neural Networks
  5. 2025Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
  6. 2026Bayesian Membership Privacy for Graph Neural Networks
  7. 2024Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
  8. 2021On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models