Related papers: GRAIN: Exact Graph Reconstruction from Gradients

Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy…

Graph-structured data is prevalent in many real-world applications, including social networks, financial systems, and molecular biology. Graph Neural Networks (GNNs) have become the de facto standard for learning from such data due to their…

Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of…

Diffusion models are becoming defector generative models, which generate exceptionally high-resolution image data. Training effective diffusion models require massive real data, which is privately owned by distributed parties. Each data…

Federated learning (FL) enables collaborative model training among multiple clients without the need to expose raw data. Its ability to safeguard privacy, at the heart of FL, has recently been a hot-button debate topic. To elaborate,…

Inferring properties of graph-structured data, e.g., the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning process is often costly for graph property learners like…

Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between different nodes. High-performance GNN models always depend…

Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, classic GCN/SAGE/GAT architectures can match graph transformers…

Graph is an important data representation ubiquitously existing in the real world. However, analyzing the graph data is computationally difficult due to its non-Euclidean nature. Graph embedding is a powerful tool to solve the graph…

Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations. However, a vast majority of…

Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the neighborhood of each node. However, this aggregation implies an…

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the server to recover…

Learning on graphs is becoming prevalent in a wide range of applications including social networks, robotics, communication, medicine, etc. These datasets belonging to entities often contain critical private information. The utilization of…

We propose Gradient Inversion Transcript (GIT), a novel generative approach for reconstructing training data from leaked gradients. GIT employs a generative attack model, whose architecture is tailored to align with the structure of the…

Recently, Graph Neural Network (GNN) has achieved remarkable success in various real-world problems on graph data. However in most industries, data exists in the form of isolated islands and the data privacy and security is also an…

Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks. Little attention has been paid to…

Federated learning (FL) has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in…

Decentralized Gradient Descent (D-GD) allows a set of users to perform collaborative learning without sharing their data by iteratively averaging local model updates with their neighbors in a network graph. The absence of direct…

Over the past few years, federated learning has become widely used in various classical machine learning fields because of its collaborative ability to train data from multiple sources without compromising privacy. However, in the area of…

Graph Neural Networks (GNNs) have gained significant attention owing to their ability to handle graph-structured data and the improvement in practical applications. However, many of these models prioritize high utility performance, such as…