LinkGuard: Link Locally Privacy-Preserving Graph Neural Networks with Integrated Denoising and Private Learning
Authors: 
Yuxin Qi, Xi Lin, Ziyao Liu, Gaolei Li, Jingyu Wang, Jianhua LiAuthors Info & Claims
Yuxin Qi, Xi Lin, Ziyao Liu, Gaolei Li, Jingyu Wang, Jianhua LiAuthors Info & ClaimsPages 593 - 596
Abstract
Recent studies have introduced privacy-preserving graph neural networks to safeguard the privacy of sensitive link information in graphs. However, existing link protection mechanisms in GNNs, particularly over decentralized nodes, struggle to strike an optimal balance between privacy and utility. We argue that a pivotal issue is the separation of noisy topology denoising and GNN private learning into distinct phases at the server side, leading to an under-denoising problem in the noisy topology. To address this, we propose a dynamic, adaptive Link LDP framework that performs noisy topology denoising on the server side in a dynamic manner. This approach aims to mitigate the impact of local noise on the GNN training process, reducing the uncertainty introduced by local noise. Furthermore, we integrate the noise generation and private training processes across all existing Link LDP GNNs into a unified framework. Experimental results demonstrate that our method surpasses existing approaches, obtaining around a 7% performance improvement under strong privacy strength and achieving a better trade-off between utility and privacy.
Supplemental Material
MP4 File
Supplemental video
- Download
- 5.03 MB
References
[1]
Eli Chien, Wei-Ning Chen, Chao Pan, Pan Li, Ayfer Ozgur, and Olgica Milenkovic. 2023. Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection. In Thirty-seventh Conference on Neural Information Processing Systems.
[2]
Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, and Prateek Jain. 2021. Node-level differentially private graph neural networks. arXiv preprint arXiv:2111.15521 (2021).
[3]
Xinlei He, Jinyuan Jia, Michael Backes, Neil Zhenqiang Gong, and Yang Zhang. 2021. Stealing links from graph neural networks. In 30th USENIX Security Symposium (USENIX Security 21). 2669--2686.
[4]
Seira Hidano and Takao Murakami. 2022. Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy. arXiv preprint arXiv:2202.10209 (2022).
[5]
Wanyu Lin, Baochun Li, and Cong Wang. 2022. Towards private learning on decentralized graphs with local differential privacy. IEEE Transactions on Information Forensics and Security, Vol. 17 (2022), 2936--2946.
[6]
Iyiola Emmanuel Olatunji, Thorben Funke, and Megha Khosla. 2023 a. Releasing Graph Neural Networks with Differential Privacy Guarantees. Transactions on Machine Learning Research (2023).
[7]
Iyiola E Olatunji, Anmar Hizber, Oliver Sihlovec, and Megha Khosla. 2023 b. Does Black-box Attribute Inference Attacks on Graph Neural Networks Constitute Privacy Risk? arXiv preprint arXiv:2306.00578 (2023).
[8]
Zhan Qin, Ting Yu, Yin Yang, Issa Khalil, Xiaokui Xiao, and Kui Ren. 2017. Generating synthetic decentralized social graphs with local differential privacy. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. 425--438.
[9]
Sina Sajadmanesh and Daniel Gatica-Perez. 2021. Locally private graph neural networks. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. 2130--2145.
[10]
Xiuling Wang and Wendy Hui Wang. 2022. Group property inference attacks against graph neural networks. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. 2871--2884.
[11]
Fan Wu, Yunhui Long, Ce Zhang, and Bo Li. 2022. Linkteller: Recovering private edges from graph neural networks via influence analysis. In 2022 IEEE Symposium on Security and Privacy (SP). IEEE, 2005--2024.
[12]
Zhilin Yang, William Cohen, and Ruslan Salakhudinov. 2016. Revisiting semi-supervised learning with graph embeddings. In International conference on machine learning. PMLR, 40--48.
[13]
Zhikun Zhang, Min Chen, Michael Backes, Yun Shen, and Yang Zhang. 2022. Inference attacks against graph neural networks. In 31st USENIX Security Symposium (USENIX Security 22). 4543--4560.
[14]
Xiaochen Zhu, Vincent YF Tan, and Xiaokui Xiao. 2023. Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. 2651--2664.
Index Terms
- LinkGuard: Link Locally Privacy-Preserving Graph Neural Networks with Integrated Denoising and Private Learning
Recommendations
Learning Privacy-Preserving Graph Convolutional Network with Partially Observed Sensitive Attributes
WWW '22: Proceedings of the ACM Web Conference 2022Recent studies have shown Graph Neural Networks (GNNs) are extremely vulnerable to attribute inference attacks. To tackle this challenge, existing privacy-preserving GNNs research assumes that the sensitive attributes of all users are known beforehand. ...
Locally Private Graph Neural Networks
CCS '21: Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications SecurityGraph Neural Networks (GNNs) have demonstrated superior performance in learning node representations for various graph inference tasks. However, learning over graph data can raise privacy concerns when nodes represent people or human-related variables ...
ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningGraph Neural Networks (GNNs) have become a popular tool for learning on graphs, but their widespread use raises privacy concerns as graph data can contain personal or sensitive information. Differentially private GNN models have been recently proposed to ...
Comments
Information & Contributors
Information
Published In
May 2024
1928 pages
ISBN:9798400701726
DOI:10.1145/3589335
- General Chairs:
- Tat-Seng Chua,
- Chong-Wah Ngo,
- Program Chairs:
- Ravi Kumar,
- Hady W. Lauw,
- Roy Ka-Wei Lee
Copyright � 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 May 2024
Check for updates
Author Tags
Qualifiers
- Short-paper
Funding Sources
- National Natural Science Foundation of China: 62202302
- National Natural Science Foundation of China: U20B2048
Conference
WWW '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,899 of 8,196 submissions, 23%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 117Total Downloads
- Downloads (Last 12 months)117
- Downloads (Last 6 weeks)28
Reflects downloads up to 16 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in