Výsledky vyhledávání - "Pham, Ngoc Duy"

Report

Enhancing Accuracy-Privacy Trade-off in Differentially Private Split Learning

Autor: Pham, Ngoc Duy, Phan, Khoa Tran, Chilamkurti, Naveen

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL process. Howeve

Externí odkaz: http://arxiv.org/abs/2310.14434

Zobrazit plný text záznamu

Report

Split Learning without Local Weight Sharing to Enhance Client-side Data Privacy

Autor: Pham, Ngoc Duy, Phan, Tran Khoa, Abuadbba, Alsharif, Gao, Yansong, Nguyen, Doan, Chilamkurti, Naveen

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the local model weights are shared among the clients for local model updat

Externí odkaz: http://arxiv.org/abs/2212.00250

Zobrazit plný text záznamu

Report

Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction

Autor: Pham, Ngoc Duy, Abuadbba, Alsharif, Gao, Yansong, Phan, Tran Khoa, Chilamkurti, Naveen

Split learning (SL) enables data privacy preservation by allowing clients to collaboratively train a deep learning model with the server without sharing raw data. However, SL still has limitations such as potential data privacy leakage and high compu

Externí odkaz: http://arxiv.org/abs/2206.04864

Zobrazit plný text záznamu