Saved in:
Bibliographic Details
Main Authors: He, Longzhu, Li, Chaozhuo, Tang, Peng, Sun, Li, Su, Sen, Yu, Philip S.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909660528771072
author He, Longzhu
Li, Chaozhuo
Tang, Peng
Sun, Li
Su, Sen
Yu, Philip S.
author_facet He, Longzhu
Li, Chaozhuo
Tang, Peng
Sun, Li
Su, Sen
Yu, Philip S.
contents Graph neural networks (GNNs) have achieved significant success in graph representation learning and have been applied to various domains. However, many real-world graphs contain sensitive personal information, such as user profiles in social networks, raising serious privacy concerns when graph learning is performed using GNNs. To address this issue, locally private graph learning protocols have gained considerable attention. These protocols leverage the privacy advantages of local differential privacy (LDP) and the effectiveness of GNN's message-passing in calibrating noisy data, offering strict privacy guarantees for users' local data while maintaining high utility (e.g., node classification accuracy) for graph learning. Despite these advantages, such protocols may be vulnerable to data poisoning attacks, a threat that has not been considered in previous research. Identifying and addressing these threats is crucial for ensuring the robustness and security of privacy-preserving graph learning frameworks. This work introduces the first data poisoning attack targeting locally private graph learning protocols. The attacker injects fake users into the protocol, manipulates these fake users to establish links with genuine users, and sends carefully crafted data to the server, ultimately compromising the utility of private graph learning. The effectiveness of the attack is demonstrated both theoretically and empirically. In addition, several defense strategies have also been explored, but their limited effectiveness highlights the need for more robust defenses.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
He, Longzhu
Li, Chaozhuo
Tang, Peng
Sun, Li
Su, Sen
Yu, Philip S.
Machine Learning
Cryptography and Security
Graph neural networks (GNNs) have achieved significant success in graph representation learning and have been applied to various domains. However, many real-world graphs contain sensitive personal information, such as user profiles in social networks, raising serious privacy concerns when graph learning is performed using GNNs. To address this issue, locally private graph learning protocols have gained considerable attention. These protocols leverage the privacy advantages of local differential privacy (LDP) and the effectiveness of GNN's message-passing in calibrating noisy data, offering strict privacy guarantees for users' local data while maintaining high utility (e.g., node classification accuracy) for graph learning. Despite these advantages, such protocols may be vulnerable to data poisoning attacks, a threat that has not been considered in previous research. Identifying and addressing these threats is crucial for ensuring the robustness and security of privacy-preserving graph learning frameworks. This work introduces the first data poisoning attack targeting locally private graph learning protocols. The attacker injects fake users into the protocol, manipulates these fake users to establish links with genuine users, and sends carefully crafted data to the server, ultimately compromising the utility of private graph learning. The effectiveness of the attack is demonstrated both theoretically and empirically. In addition, several defense strategies have also been explored, but their limited effectiveness highlights the need for more robust defenses.
title Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2506.09803