A Privacy-Preserving Graph Neural Network for Network Intrusion Detection
With the ever-growing attention on communication security, machine learning-based
network intrusion detection system (NIDS) is widely utilized to meet different security …
network intrusion detection system (NIDS) is widely utilized to meet different security …
Privacy-Preserved Neural Graph Similarity Learning
To develop effective and efficient graph similarity learning (GSL) models, a series of data-
driven neural algorithms have been proposed in recent years. Although GSL models are …
driven neural algorithms have been proposed in recent years. Although GSL models are …
Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs
T Zhao, H Hu, L Cheng - Proceedings of the 32nd ACM International …, 2023 - dl.acm.org
Graph Neural Networks (GNNs) are powerful tools for learning representations on graphs,
such as social networks. However, their vulnerability to privacy inference attacks restricts …
such as social networks. However, their vulnerability to privacy inference attacks restricts …
LinkGuard: Link Locally Privacy-Preserving Graph Neural Networks with Integrated Denoising and Private Learning
Y Qi, X Lin, Z Liu, G Li, J Wang, J Li - … Proceedings of the ACM on Web …, 2024 - dl.acm.org
Recent studies have introduced privacy-preserving graph neural networks to safeguard the
privacy of sensitive link information in graphs. However, existing link protection mechanisms …
privacy of sensitive link information in graphs. However, existing link protection mechanisms …
Heterogeneous graph neural network with semantic-aware differential privacy guarantees
Most social networks can be modeled as heterogeneous graphs. Recently, advanced graph
learning methods exploit the rich node properties and topological relationships for …
learning methods exploit the rich node properties and topological relationships for …
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 …
A privacy preserving graph neural networks framework by protecting user's attributes
L Zhou, J Wang, D Fan, H Zhang, K Zhong - Physica A: Statistical …, 2023 - Elsevier
Graph neural networks (GNNs) can learn the node representations to capture both node
features and graph topology information through the message passing mechanism …
features and graph topology information through the message passing mechanism …
Privacy-Preserving Machine Learning on Graphs
S Sajadmanesh - 2023 - infoscience.epfl.ch
Abstract Graph Neural Networks (GNNs) have emerged as a powerful tool for learning on
graphs, demonstrating exceptional performance in various domains. However, as GNNs …
graphs, demonstrating exceptional performance in various domains. However, as GNNs …
Efficient privacy preserving graph neural network for node classification
Graph Neural Networks (GNNs) as an emerging technique have shown excellent
performance in a variety of fields, such as social networks and recommendation systems …
performance in a variety of fields, such as social networks and recommendation systems …
Privacy-enhanced graph neural network for decentralized local graphs
With the ever-growing interest in modeling complex graph structures, graph neural networks
(GNN) provide a generalized form of exploiting non-Euclidean space data. However, the …
(GNN) provide a generalized form of exploiting non-Euclidean space data. However, the …