Privacy and communication constraints are two major bottlenecks in federated learning (FL) and analytics (FA). We study the optimal accuracy of mean and frequency estimation …
J Fu, Y Hong, X Ling, L Wang, X Ran, Z Sun… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, privacy and security concerns in machine learning have promoted trusted federated learning to the forefront of research. Differential privacy has emerged as the de …
K Edemacu, X Wu - arXiv preprint arXiv:2404.06001, 2024 - arxiv.org
Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have …
Graph Neural Networks have achieved tremendous success in modeling complex graph data in a variety of applications. However, there are limited studies investigating privacy …
O Räisä, J Jälkö, A Honkela - arXiv preprint arXiv:2402.03990, 2024 - arxiv.org
We study the effect of the batch size to the total gradient variance in differentially private stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness …
H Wang, S Pang, Z Lu, Y Rao, Y Zhou, M Xue - 2024 - usenix.org
Utilizing sensitive images (eg, human faces) for training DL models raises privacy concerns. One straightforward solution is to replace the private images with synthetic ones generated …
H Chen, J Pang, Y Zhao, S Giddens… - Journal of the …, 2024 - academic.oup.com
Objectives Clinical trial data sharing is crucial for promoting transparency and collaborative efforts in medical research. Differential privacy (DP) is a formal statistical technique for …
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks by conditioning on demonstrations of question-answer pairs and it has been shown to have …
THH Chan, H Xie, M Zhao - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
We study a private variant of ADMM with (strongly) convex objective functions. We consider a privacy model in which each iteration corresponds to a user whose private function is …