Locally Private Graph Neural Networks

Sajadmanesh, Sina; Gática-Pérez, Daniel

doi:10.48550/arxiv.2006.05535

Cited by 5 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the privacy budget and the mechanism to be protected, certain levels of Gaussian noise or Laplace noise will be injected to achieve a differentially private mechanism. Recently, various differential-privacy preserving deep learning methods [1,8,141,152] are proposed to protect the training data privacy. For instance, NoisySGD [1] adds noises to the gradients during model training so the trained model parameters will not leak training data with certain guarantee.…”

Section: Differentialmentioning

confidence: 99%

“…In differential privacy, a trusted curator will be required to apply calibrated noise to produce DP. To handle the situation of untrusted curator, local differential privacy methods [8,152] that perturbs users' data locally before uploading to the central server are also investigated for privacy protection.…”

Section: Differentialmentioning

confidence: 99%

“…To protect the privacy of graph-structured data, many differential privacy preserving network embedding methods are investigated [136,152,208,228]. For instance, DPNE [208] applies perturbations on the objective function of learning network embeddings.…”

Section: Differentialmentioning

confidence: 99%

“…In [227], a perturbed gradient descent method that guarantees the privacy of graph embeddings learned by matrix factorization is proposed. More recently, several works [136,152] that focus on differentially private GNNs are explored. For example, the locally private GNN [152] adopts local differential privacy [92] to protect the privacy of node features by perturbing the user's features locally.…”

Section: Differentialmentioning

confidence: 99%

See 3 more Smart Citations

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Dai¹,

Zhao²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have made rapid developments in the recent years. Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society. For example, existing works demonstrate that attackers can fool the GNNs to give the outcome they desire with unnoticeable perturbation on training graph. GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias. Consequently, trustworthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users' trust in GNNs. In this paper, we give a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability. For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. We also discuss the future research directions of each aspect and connections between these aspects to help achieve trustworthiness.

show abstract

Section: Differentialmentioning

confidence: 99%

Section: Differentialmentioning

confidence: 99%

Section: Differentialmentioning

confidence: 99%

Section: Differentialmentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Dai¹,

Zhao²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Existing works on privacy-preserving GNNs mainly focussed on a distributed setting in which the node feature values or/and labels are assumed to be private and distributed among multiple distrusting parties [20,21,25,27]. Sajadmanesh and Gatica-Perez [20] assumed that only the node features are sensitive while the graph structure is publicly available and developed a local differential privacy mechanism to tackle the problem of node-level privacy.…”

Section: Related Workmentioning

confidence: 99%

Releasing Graph Neural Networks with Differential Privacy Guarantees

Olatunji,

Funke,

Khosla

2021

Preprint

View full text Add to dashboard Cite

With the increasing popularity of Graph Neural Networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs. More notably, GNNs are vulnerable to privacy attacks, such as membership inference attacks, even if only blackbox access to the trained model is granted. To build defenses, differential privacy has emerged as a mechanism to disguise the sensitive data in training datasets. Following the strategy of Private Aggregation of Teacher Ensembles (PATE), recent methods leverage a large ensemble of teacher models. These teachers are trained on disjoint subsets of private data and are employed to transfer knowledge to a student model, which is then released with privacy guarantees. However, splitting graph data into many disjoint training sets may destroy the structural information and adversely affect accuracy. We propose a new graph-specific scheme of releasing a student GNN, which avoids splitting private training data altogether. The student GNN is trained using public data, partly labeled privately using the teacher GNN models trained exclusively for each query node. We theoretically analyze our approach in the Rènyi differential privacy framework and provide privacy guarantees. Besides, we show the solid experimental performance of our method compared to several baselines, including the PATE baseline adapted for graph-structured data. Our anonymized code is available.

show abstract

Advances in Differential Privacy and Differentially Private Machine Learning

Das,

Mishra

2024

Information Technology Security

View full text Add to dashboard Cite

Locally Private Graph Neural Networks

Cited by 5 publications

References 0 publications

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Releasing Graph Neural Networks with Differential Privacy Guarantees

Advances in Differential Privacy and Differentially Private Machine Learning

Contact Info

Product

Resources

About