GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

• URL: http://arxiv.org/abs/2203.00949v1
• Date: Wed, 2 Mar 2022 08:58:07 GMT
• Title: GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation
• Authors: Sina Sajadmanesh, Ali Shahin Shamsabadi, Aur\'elien Bellet, Daniel Gatica-Perez
• Abstract summary: 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.
• Score: 19.247325210343035
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNNs) are powerful models designed for graph data that learn node representation by recursively aggregating information from each node's local neighborhood. However, despite their state-of-the-art performance in predictive graph-based applications, recent studies have shown that GNNs can raise significant privacy concerns when graph data contain sensitive information. As a result, in this paper, we study the problem of learning GNNs with Differential Privacy (DP). We propose GAP, a novel differentially private GNN that safeguards the privacy of nodes and edges using aggregation perturbation, i.e., adding calibrated stochastic noise to the output of the GNN's aggregation function, which statistically obfuscates the presence of a single edge (edge-level privacy) or a single node and all its adjacent edges (node-level privacy). To circumvent the accumulation of privacy cost at every forward pass of the model, we tailor the GNN architecture to the specifics of private learning. In particular, we first precompute private aggregations by recursively applying neighborhood aggregation and perturbing the output of each aggregation step. Then, we privately train a deep neural network on the resulting perturbed aggregations for any node-wise classification task. A major advantage of GAP over previous approaches is that we guarantee edge-level and node-level DP not only for training, but also at inference time with no additional costs beyond the training's privacy budget. We theoretically analyze the formal privacy guarantees of GAP using R\'enyi DP. Empirical experiments conducted over three real-world graph datasets demonstrate that GAP achieves a favorable privacy-accuracy trade-off and significantly outperforms existing approaches.

Related papers

• Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation [79.64626707978418]
  We propose using link local differential privacy over decentralized nodes to train graph neural networks. Our approach spends the privacy budget separately on links and degrees of the graph for the server to better denoise the graph topology. Our approach outperforms existing methods in terms of accuracy under varying privacy budgets.
  arXiv  Detail & Related papers  (2023-09-06T17:53:31Z)
• 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)
• Differentially Private Graph Neural Network with Importance-Grained Noise Adaption [6.319864669924721]
  Graph Neural Networks (GNNs) with differential privacy have been proposed to preserve graph privacy when nodes represent personal and sensitive information. We study the problem of importance-grained privacy, where nodes contain personal data that need to be kept private but are critical for training a GNN. We propose NAP-GNN, a node-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information.
  arXiv  Detail & Related papers  (2023-08-09T13:18:41Z)
• Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection [38.96828804683783]
  GNNs can inadvertently expose sensitive user information and interactions through their model predictions. Applying standard DP approaches to GNNs directly is not advisable due to two main reasons. We propose a new framework termed Graph Differential Privacy (GDP), specifically tailored to graph learning.
  arXiv  Detail & Related papers  (2023-07-12T19:29:06Z)
• ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees [8.79398901328539]
  Graph Neural Networks (GNNs) have become a popular tool for learning on graphs, but their widespread use raises privacy concerns. We propose a new differentially private GNN called ProGAP that uses a progressive training scheme to improve such accuracy-privacy trade-offs.
  arXiv  Detail & Related papers  (2023-04-18T12:08:41Z)
• Privacy-Preserved Neural Graph Similarity Learning [99.78599103903777]
  We propose a novel Privacy-Preserving neural Graph Matching network model, named PPGM, for graph similarity learning. To prevent reconstruction attacks, the proposed model does not communicate node-level representations between devices. To alleviate the attacks to graph properties, the obfuscated features that contain information from both vectors are communicated.
  arXiv  Detail & Related papers  (2022-10-21T04:38:25Z)
• Model Inversion Attacks against Graph Neural Networks [65.35955643325038]
  We study model inversion attacks against Graph Neural Networks (GNNs) In this paper, we present GraphMI to infer the private training graph data. Our experimental results show that such defenses are not sufficiently effective and call for more advanced defenses against privacy attacks.
  arXiv  Detail & Related papers  (2022-09-16T09:13:43Z)
• Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily [58.76759997223951]
  We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs. We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
  arXiv  Detail & Related papers  (2022-03-19T14:26:43Z)
• Node-Level Differentially Private Graph Neural Networks [14.917945355629563]
  Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data. This work formally defines the problem of learning 1-layer GNNs with node-level privacy. We provide an algorithmic solution with a strong differential privacy guarantee.
  arXiv  Detail & Related papers  (2021-11-23T16:18:53Z)
• Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
  Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
  arXiv  Detail & Related papers  (2020-06-26T17:03:06Z)
• Locally Private Graph Neural Networks [12.473486843211573]
  We study the problem of node data privacy, where graph nodes have potentially sensitive data that is kept private. We develop a privacy-preserving, architecture-agnostic GNN learning algorithm with formal privacy guarantees. Experiments conducted over real-world datasets demonstrate that our method can maintain a satisfying level of accuracy with low privacy loss.
  arXiv  Detail & Related papers  (2020-06-09T22:36:06Z)

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.