.png){kind=icon}
返回
A Federated Learning Framework Based on Differentially Private Continuous Data Release
.png){kind=icon}
PRE
AI
DOI：10.1109/TDSC.2024.3364060.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Federated learning (FL) provides a learning framework without participants sharing local raw data, but individual privacy is still at risk of disclosure through attacking the trained models. Due to the strong privacy guarantee, differential privacy (DP) is widely applied to FL to avoid privacy leakage. Traditional private learning adds noise directly to the gradients. The continuous accumulated noise on parameter models severely impairs learning effectiveness. To solve this problem, we introduce the idea of differentially private continuous data release (DPCR) into FL and propose an FL framework based on DPCR (FL-DPCR). Meanwhile, our proposed Equivalent Aggregation Theorem demonstrates that DPCR effectively reduces the overall error added to parameter models and improves FL's accuracy. To improve FL-DPCR's learning effectiveness, we introduce Matrix Mechanism to construct a release strategy and design a binary-indexed-tree (BIT) based DPCR model for Gaussian mechanism (BCRG). By solving a complex nonlinear programming problem with negative exponents, BCRG achieves optimal release accuracy efficiently. Besides, we exploit the residual privacy budget to boost the accuracy further and propose an advanced BCRG version (ABCRG). Our experiments show that, compared to traditional FL with DP, our achievements improve the accuracy with gains ranging from 3.4% on FMNIST to 65.7% on PAMAP2.
Keyword:
Privacy
Data models
Artificial intelligence
Differential privacy
Biomedical imaging
Computational modeling
Security
Federated learning
differential privacy
continuous data release
binary indexed tree
matrix mechanism
期刊
IF:
7.5
论文数:
2.5K
被引数:
9.6K
机构
引用论文
Ionic liquids derived from trialkylsulfonium bromides: Physicochemical properties and potential applications溴化三烷基锍衍生的离子液体: 物理化学性质和潜在应用
PREAI
分享收藏Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data医学联合学习: 在不共享患者数据的情况下促进多机构合作.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏
查看更多内容