# DP-GPL: Differentially Private Graph Prompt Learning

arXiv: https://arxiv.org/abs/2503.10544 · HTML: https://mlsanity.com/paper/2503.10544/

## 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 (most cited first, 30 of 38)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Scalable Private Learning with PATE](https://mlsanity.com/paper/1802.08908/) (2018)
- [Rethinking Graph Neural Networks for Anomaly Detection](https://mlsanity.com/paper/2205.15508/) (2022)
- [SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation](https://mlsanity.com/paper/2202.03104/) (2022)
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://mlsanity.com/paper/2302.08043/) (2023)
- [All in One: Multi-task Prompting for Graph Neural Networks](https://mlsanity.com/paper/2307.01504/) (2023)
- [Universal Prompt Tuning for Graph Neural Networks](https://mlsanity.com/paper/2209.15240/) (2022)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models](https://mlsanity.com/paper/2305.15594/) (2023)
- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer](https://mlsanity.com/paper/2312.03724/) (2023)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [Can Large Language Models Empower Molecular Property Prediction?](https://mlsanity.com/paper/2307.07443/) (2023)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection](https://mlsanity.com/paper/2309.03057/) (2023)
- [Releasing Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2109.08907/) (2021)
- [On the Privacy Risk of In-context Learning](https://mlsanity.com/paper/2411.10512/) (2024)
- [Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction](https://mlsanity.com/paper/2006.01963/) (2020)
- [ProG: A Graph Prompt Learning Benchmark](https://mlsanity.com/paper/2406.05346/) (2024)

## 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.