Incentivizing differentially private federated learning: A multidimensional contract approach

M Wu, D Ye, J Ding, Y Guo, R Yu… - IEEE Internet of Things …, 2021 - ieeexplore.ieee.org
Federated learning is a promising tool in the Internet-of-Things (IoT) domain for training a
machine learning model in a decentralized manner. Specifically, the data owners (eg, IoT …

Adaptive privacy preserving deep learning algorithms for medical data

X Zhang, J Ding, M Wu, STC Wong… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep learning holds a great promise of revolutionizing healthcare and medicine.
Unfortunately, various inference attack models demonstrated that deep learning puts …

Differentially private and communication efficient collaborative learning

J Ding, G Liang, J Bi, M Pan - Proceedings of the AAAI Conference on …, 2021 - ojs.aaai.org
Collaborative learning has received huge interests due to its capability of exploiting the
collective computing power of the wireless edge devices. However, during the learning …

From noisy fixed-point iterations to private ADMM for centralized and federated learning

E Cyffers, A Bellet, D Basu - International Conference on …, 2023 - proceedings.mlr.press
We study differentially private (DP) machine learning algorithms as instances of noisy fixed-
point iterations, in order to derive privacy and utility results from this well-studied framework …

Boosting accuracy of differentially private federated learning in industrial IoT with sparse responses

L Cui, J Ma, Y Zhou, S Yu - IEEE Transactions on Industrial …, 2022 - ieeexplore.ieee.org
Empowered by 5G, it has been extensively explored by existing works on the deployment of
differentially private federated learning (DPFL) in the Industrial Internet of Things (IIoT) …

Preserving Privacy in Fine-grained Data Distillation with Sparse Answers for Efficient Edge Computing

K Pan, M Gong, K Feng, H Li - IEEE Internet of Things Journal, 2024 - ieeexplore.ieee.org
In the field of internet of things (IoT), data distillation has been thought of as a key method to
condense the original real dataset into a tiny synthetic dataset with less training burden …

An Optimized Sparse Response Mechanism for Differentially Private Federated Learning

J Ma, Y Zhou, L Cui, S Guo - IEEE Transactions on Dependable …, 2023 - ieeexplore.ieee.org
Federated Learning (FL) enables geo-distributed clients to collaboratively train a learning
model without exposing their private data. By only exposing local model parameters, FL well …

Federated learning of oligonucleotide drug molecule thermodynamics with differentially private admm-based svm

S Tavara, A Schliep, D Basu - Joint European Conference on Machine …, 2021 - Springer
A crucial step to assure drug safety is predicting off-target binding. For oligonucleotide drugs
this requires learning the relevant thermodynamics from often large-scale data distributed …

Balancing Privacy and Accuracy using Significant Gradient Protection in Federated Learning

B Zhang, Y Mao, X He, H Huang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Previous state-of-the-art studies have demonstrated that adversaries can access sensitive
user data by membership inference attacks (MIAs) in Federated Learning (FL). Introducing …

Distributed and federated learning of support vector machines and applications

S Tavara - 2022 - diva-portal.org
Machine Learning (ML) has achieved remarkable success in solving classification,
regression, and related problems over the past decade. In particular the exponential growth …