61 citations · 90 across the 13 of their papers we have counts for
13 papers
When Is Distributed Nonlinear Aggregation Private? Optimality and Information-Theoretical Bounds
Wenrui Yu, Jaron Skovsted Gundersen, Richard Heusdens +1
Nonlinear aggregation is central to modern distributed systems, yet its privacy behavior is far less understood than that of linear aggregation. Unlike linear aggregation where mat…
Optimal Privacy-Preserving Distributed Median Consensus
Wenrui Yu, Qiongxiu Li, Richard Heusdens +1
Distributed median consensus has emerged as a critical paradigm in multi-agent systems due to the inherent robustness of the median against outliers and anomalies in measurement. D…
Privacy-Preserving Distributed Maximum Consensus Without Accuracy Loss
Wenrui Yu, Richard Heusdens, Jun Pang +1
In distributed networks, calculating the maximum element is a fundamental task in data analysis, known as the distributed maximum consensus problem. However, the sensitive nature o…
Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
Wenrui Yu, Qiongxiu Li, Milan Lopuhaä-Zwakenberg +2
Federated learning (FL) emerged as a paradigm designed to improve data privacy by enabling data to reside at its source, thus embedding privacy as a core consideration in FL archit…
Privacy-Preserving Distributed Optimisation using Stochastic PDMM
Sebastian O. Jordan, Qiongxiu Li, Richard Heusdens
Privacy-preserving distributed processing has received considerable attention recently. The main purpose of these algorithms is to solve certain signal processing tasks over a netw…
On the privacy of federated Clustering: A Cryptographic View
Qiongxiu Li, Lixia Luo
The privacy concern in federated clustering has attracted considerable attention in past decades. Many privacy-preserving clustering algorithms leverage cryptographic techniques li…
Topology-Dependent Privacy Bound For Decentralized Federated Learning
Qiongxiu Li, Wenrui Yu, Changlong Ji +1
Decentralized Federated Learning (FL) has attracted significant attention due to its enhanced robustness and scalability compared to its centralized counterpart. It pivots on peer-…
Adaptive Differentially Quantized Subspace Perturbation (ADQSP): A Unified Framework for Privacy-Preserving Distributed Average Consensus
Qiongxiu Li, Jaron Skovsted Gundersen, Milan Lopuhaa-Zwakenberg +1
Privacy-preserving distributed average consensus has received significant attention recently due to its wide applicability. Based on the achieved performances, existing approaches…
Privacy-Preserving Distributed Expectation Maximization for Gaussian Mixture Model using Subspace Perturbation
Qiongxiu Li, Jaron Skovsted Gundersen, Katrine Tjell +2
Privacy has become a major concern in machine learning. In fact, the federated learning is motivated by the privacy concern as it does not allow to transmit the private data but on…
On the Privacy Effect of Data Enhancement via the Lens of Memorization
Xiao Li, Qiongxiu Li, Zhanhao Hu +1
Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated…
Communication efficient privacy-preserving distributed optimization using adaptive differential quantization
Qiongxiu Li, Richard Heusdens, Mads Græsbøll Christensen
Privacy issues and communication cost are both major concerns in distributed optimization. There is often a trade-off between them because the encryption methods required for priva…
Privacy-Preserving Distributed Processing: Metrics, Bounds, and Algorithms
Qiongxiu Li, Jaron Skovsted Gundersen, Richard Heusdens +1
Privacy-preserving distributed processing has recently attracted considerable attention. It aims to design solutions for conducting signal processing tasks over networks in a decen…
Privacy-Preserving Distributed Optimization via Subspace Perturbation: A General Framework
Qiongxiu Li, Richard Heusdens, Mads Græsbøll Christensen
As the modern world becomes increasingly digitized and interconnected, distributed signal processing has proven to be effective in processing its large volume of data. However, a m…