Learning privacy-preserving graph convolutional network with partially observed sensitive attributes
Recent studies have shown Graph Neural Networks (GNNs) are extremely vulnerable to
attribute inference attacks. To tackle this challenge, existing privacy-preserving GNNs …
attribute inference attacks. To tackle this challenge, existing privacy-preserving GNNs …
Does black-box attribute inference attacks on graph neural networks constitute privacy risk?
IE Olatunji, A Hizber, O Sihlovec, M Khosla - arXiv preprint arXiv …, 2023 - arxiv.org
Graph neural networks (GNNs) have shown promising results on real-life datasets and
applications, including healthcare, finance, and education. However, recent studies have …
applications, including healthcare, finance, and education. However, recent studies have …
Heterogeneous graph neural network for privacy-preserving recommendation
Social networks are considered to be heterogeneous graph neural networks (HGNNs) with
deep learning technological advances. HGNNs, compared to homogeneous data, absorb …
deep learning technological advances. HGNNs, compared to homogeneous data, absorb …
Linkteller: Recovering private edges from graph neural networks via influence analysis
Graph structured data have enabled several successful applications such as
recommendation systems and traffic prediction, given the rich node features and edges …
recommendation systems and traffic prediction, given the rich node features and edges …
Adversary for social good: Leveraging attribute-obfuscating attack to protect user privacy on social networks
As social networks become indispensable for people's daily lives, inference attacks pose
significant threat to users' privacy where attackers can infiltrate users' information and infer …
significant threat to users' privacy where attackers can infiltrate users' information and infer …
Node-level differentially private graph neural networks
Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data
and computing node-level representations via aggregation of information from the …
and computing node-level representations via aggregation of information from the …
Netfense: Adversarial defenses against privacy attacks on neural networks for graph data
IC Hsieh, CT Li - IEEE Transactions on Knowledge and Data …, 2021 - ieeexplore.ieee.org
Recent advances in protecting node privacy on graph data and attacking graph neural
networks (GNNs) gain much attention. The eye does not bring these two essential tasks …
networks (GNNs) gain much attention. The eye does not bring these two essential tasks …
Locally private graph neural networks
S Sajadmanesh, D Gatica-Perez - … of the 2021 ACM SIGSAC conference …, 2021 - dl.acm.org
Graph Neural Networks (GNNs) have demonstrated superior performance in learning node
representations for various graph inference tasks. However, learning over graph data can …
representations for various graph inference tasks. However, learning over graph data can …
Demystifying uneven vulnerability of link stealing attacks against graph neural networks
While graph neural networks (GNNs) dominate the state-of-the-art for exploring graphs in
real-world applications, they have been shown to be vulnerable to a growing number of …
real-world applications, they have been shown to be vulnerable to a growing number of …
Graph privacy funnel: A variational approach for privacy-preserving representation learning on graphs
This paper investigates the problem of learning privacy-preserving graph representations
with graph neural networks (GNNs). Different from existing works based on adversarial …
with graph neural networks (GNNs). Different from existing works based on adversarial …