GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

Résumé

In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP). We propose a novel differentially private GNN based on Aggregation Perturbation (GAP), which adds stochastic noise to the GNN's aggregation function to statistically obfuscate the presence of a single edge (edge-level privacy) or a single node and all its adjacent edges (node-level privacy). Tailored to the specifics of private learning, GAP's new architecture is composed of three separate modules: (i) the encoder module, where we learn private node embeddings without relying on the edge information; (ii) the aggregation module, where we compute noisy aggregated node embeddings based on the graph structure; and (iii) the classification module, where we train a neural network on the private aggregations for node classification without further querying the graph edges. GAP's major advantage over previous approaches is that it can benefit from multi-hop neighborhood aggregations, and guarantees both edge-level and node-level DP not only for training, but also at inference with no additional costs beyond the training's privacy budget. We analyze GAP's formal privacy guarantees using Rényi DP and conduct empirical experiments over three real-world graph datasets. We demonstrate that GAP offers significantly better accuracy-privacy trade-offs than state-of-the-art DP-GNN approaches and naive MLP-based baselines. Our code is publicly available at https://github.com/sisaman/GAP.
Fichier principal
Vignette du fichier
2203.00949.pdf (876.86 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03905068 , version 1 (17-12-2022)

Identifiants

Citer

Sina Sajadmanesh, Ali Shahin Shamsabadi, Aurélien Bellet, Daniel Gatica-Perez. GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation. USENIX Security 2023 - 32nd USENIX Security Symposium, Aug 2023, Anaheim, United States. ⟨hal-03905068⟩
145 Consultations
69 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More