Convergent Privacy Framework with Contractive GNN Layers for Multi-hop Aggregations

• URL: http://arxiv.org/abs/2506.22727v1
• Date: Sat, 28 Jun 2025 02:17:53 GMT
• Title: Convergent Privacy Framework with Contractive GNN Layers for Multi-hop Aggregations
• Authors: Yu Zheng, Chenang Li, Zhou Li, Qingsong Wang,
• Abstract summary: Differential privacy (DP) has been integrated into graph neural networks (GNNs) to protect sensitive structural information.<n>We propose a simple yet effective Contractive Graph Layer (CGL) that ensures the contractiveness required for theoretical guarantees.<n>Our framework, CARIBOU, supports both training and inference, equipped with a contractive aggregation module, a privacy allocation module, and a privacy auditing module.
• Score: 9.399260063250635
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differential privacy (DP) has been integrated into graph neural networks (GNNs) to protect sensitive structural information, e.g., edges, nodes, and associated features across various applications. A common approach is to perturb the message-passing process, which forms the core of most GNN architectures. However, existing methods typically incur a privacy cost that grows linearly with the number of layers (Usenix Security'23), ultimately requiring excessive noise to maintain a reasonable privacy level. This limitation becomes particularly problematic when deep GNNs are necessary to capture complex and long-range interactions in graphs. In this paper, we theoretically establish that the privacy budget can converge with respect to the number of layers by applying privacy amplification techniques to the message-passing process, exploiting the contractive properties inherent to standard GNN operations. Motivated by this analysis, we propose a simple yet effective Contractive Graph Layer (CGL) that ensures the contractiveness required for theoretical guarantees while preserving model utility. Our framework, CARIBOU, supports both training and inference, equipped with a contractive aggregation module, a privacy allocation module, and a privacy auditing module. Experimental evaluations demonstrate that CARIBOU significantly improves the privacy-utility trade-off and achieves superior performance in privacy auditing tasks.

Related papers

• Differentially Private Relational Learning with Entity-level Privacy Guarantees [17.567309430451616]
  This work presents a principled framework for relational learning with formal entity-level DP guarantees.<n>We introduce an adaptive gradient clipping scheme that modulates clipping thresholds based on entity occurrence frequency.<n>These contributions lead to a tailored DP-SGD variant for relational data with provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-06-10T02:03:43Z)
• Urania: Differentially Private Insights into AI Use [104.7449031243196]
  $Urania$ provides end-to-end privacy protection by leveraging DP tools such as clustering, partition selection, and histogram-based summarization.<n>Results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy.
  arXiv  Detail & Related papers  (2025-06-05T07:00:31Z)
• Convergent Differential Privacy Analysis for General Federated Learning: the $f$-DP Perspective [57.35402286842029]
  Federated learning (FL) is an efficient collaborative training paradigm with a focus on local privacy. differential privacy (DP) is a classical approach to capture and ensure the reliability of private protections.
  arXiv  Detail & Related papers  (2024-08-28T08:22:21Z)
• Preserving Node-level Privacy in Graph Neural Networks [8.823710998526705]
  We propose a solution that addresses the issue of node-level privacy in Graph Neural Networks (GNNs) Our protocol consists of two main components: 1) a sampling routine called HeterPoisson, which employs a specialized node sampling strategy and a series of tailored operations to generate a batch of sub-graphs with desired properties, and 2) a randomization routine that utilizes symmetric Laplace noise instead of the commonly used Gaussian noise. Our protocol enables GNN learning with good performance, as demonstrated by experiments on five real-world datasets.
  arXiv  Detail & Related papers  (2023-11-12T16:21:29Z)
• 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)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation [19.247325210343035]
  Graph Neural Networks (GNNs) are powerful models designed for graph data that learn node representation. Recent studies have shown that GNNs can raise significant privacy concerns when graph data contain sensitive information. We propose GAP, a novel differentially private GNN that safeguards privacy of nodes and edges.
  arXiv  Detail & Related papers  (2022-03-02T08:58:07Z)
• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy [67.4471689755097]
  This paper empirically demonstrates that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity. We provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates.
  arXiv  Detail & Related papers  (2021-06-25T14:47:19Z)
• DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation [15.63770709526671]
  We propose a scalable privacy-preserving generative model DATALENS. We show that, DATALENS significantly outperforms other baseline DP generative models. We adapt the proposed TOPAGG approach, which is one of the key building blocks in DATALENS, to DP SGD training.
  arXiv  Detail & Related papers  (2021-03-20T06:14:19Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

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.