Federated Learning With Differential Privacy: Algorithms and Performance Analysis

Kang Wei; Jun Li; Ming Ding; Chuan Ma; Howard H. Yang; Farhad Farokhi; Shi Jin; Tony Q. S. Quek; H. Vincent Poor

doi:10.1109/tifs.2020.2988575

journal article Jan 01, 2020

Federated Learning With Differential Privacy: Algorithms and Performance Analysis

Kang Wei Jun Li

IEEE Transactions on Information Forensics and Security Vol. 15 pp. 3454-3469 · Institute of Electrical and Electronics Engineers (IEEE)

View at Publisher Save 10.1109/tifs.2020.2988575

Topics

No keywords indexed for this article. Browse by subject →

References

38

[1]

nesterov Introductory Lectures on Convex Optimization A Basic Course (2014)

[2]

ryffel "A generic framework for privacy preserving deep learning" arXiv 1811 04017 (2018)

[3]

brendan mcmahan "Learning differentially private recurrent language models" arXiv 1710 06963 (2017)

[4]

li "Differentially private meta-learning" arXiv 1909 05830 (2019)

[5]

wu "The value of collaboration in convex machine learning with differential privacy" arXiv 1906 09679 (2019)

[6]

Gradient-based learning applied to document recognition

Y. Lecun, L. Bottou, Y. Bengio et al.

Proceedings of the IEEE 10.1109/5.726791

[7]

10.1145/2810103.2813677

[8]

truex "A hybrid approach to privacy-preserving federated learning" arXiv 1812 03224 (2018)

[9]

geyer "Differentially private federated learning: A client level perspective" arXiv 1712 07557 (2017)

[10]

10.1145/3298981

[11]

li "Federated learning: Challenges, methods, and future directions" arXiv 1908 07873 (2019)

[12]

10.1109/infocom.2019.8737464

[13]

10.1109/tcomm.2019.2944169

[14]

10.1109/icc.2019.8761267

[15]

10.1109/icassp40776.2020.9053740

[16]

10.1109/cdc.2012.6426626

[17]

xiangru "Asynchronous parallel stochastic gradient for nonconvex optimization" Proc ACM NIPS (2015)

[18]

lian "Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent" Proc ACM NIPS (2017)

[19]

li "Federated optimization in heterogeneous networks" arXiv 1812 06127 (2018)

[20]

Local Differential Private Data Aggregation for Discrete Distribution Estimation

Shaowei Wang, Liusheng Huang, Yiwen Nie et al.

IEEE Transactions on Parallel and Distributed Syst... 10.1109/tpds.2019.2899097

[21]

10.1109/mnet.001.1800510

[22]

10.1109/icde.2019.00063

[23]

10.1109/jsac.2019.2933890

[24]

brendan mcmahan "Communication-efficient learning of deep networks from decentralized data" arXiv 1602 05629 (2016)

[25]

10.1145/2976749.2978318

[26]

10.1109/comst.2018.2844341

[27]

mohammad "Adaptive task allocation for asynchronous federated mobile edge learning" arXiv 1905 01656 (2019)

[28]

kone?ný "Federated learning: Strategies for improving communication efficiency" arXiv 1610 05492 (2016)

[29]

10.1109/jiot.2019.2907245

[30]

10.1109/mnet.2019.1800286

[31]

10.1109/tmc.2018.2853746

[32]

10.1109/jsac.2019.2904348

[33]

10.1109/infocom.2019.8737416

[34]

10.1145/2810103.2813687

[35]

The Algorithmic Foundations of Differential Privacy

Cynthia Dwork, Aaron Roth

Foundations and Trends® in Theoretical Computer Sc... 10.1561/0400000042

[36]

ma "On safeguarding privacy and security in the framework of federated learning" arXiv 1909 06512 (2019)

[37]

10.1145/2660267.2660348

[38]

10.1145/1065167.1065184

Cited By

1,971

Federated learning for intelligent transportation systems: Emerging trends, challenges and future directions

Muhammad Babar, Basit Qureshi · 2026

Computer Science Review

EPRA-VFL: A privacy-preserving and efficient verifiable federated learning scheme with robust aggregation

Yujie Li, Yi Sun · 2026

Journal of Parallel and Distributed...

Beyond LDP-FL: Independent Uplink–Downlink Privacy Protection in Federated Learning

Dongrun Li, Yun Zeng · 2026

IEEE Transactions on Network Scienc...

Learning to Incentivize: Convergence-Guaranteed Federated Learning via Client Quality Discovery

Jiajun Wang, Jianxiong Guo · 2026

IEEE Transactions on Mobile Computi...

Federated machine learning for cross-bank credit card fraud detection: A privacy-preserving framework

Dhanveer Singh, Raja Chattopadhyay · 2026

African Journal of Science, Technol...

SLAPE: Secure Lightweight Authentication for Privacy-Enhanced Federated Learning in Industrial Internet of Things

Shanyao Ren, Jianwei Liu · 2026

IEEE Internet of Things Journal

Federated Learning-Based Anomaly Detection with Isolation Forest in the IoT-Edge Continuum

Haolong Xiang, Xuyun Zhang · 2026

ACM Transactions on Multimedia Comp...

Quid pro Quo: Information disclosure for AI feedback in Human-AI collaboration

Izabel Cvetkovic, Imke Grashoff · 2025

Computers in Human Behavior: Artifi...

Privacy-preserving Federated Learning and Uncertainty Quantification in Medical Imaging

Nikolas Koutsoubis, Asim Waqas · 2025

Radiology: Artificial Intelligence

Protecting Your Attention During Distributed Graph Learning: Efficient Privacy-Preserving Federated Graph Attention Network

Jinhao Zhou, Jun Wu · 2025

IEEE Transactions on Information Fo...

Federated reinforcement learning for sustainable and cost-efficient energy management

J. Sievers, P. Henrich · 2025

Energy and AI

Efficient Federated Learning via Adaptive Model Pruning for Internet of Vehicles With a Constrained Latency

Xing Chang, Mohammad S. Obaidat · 2025

IEEE Transactions on Sustainable Co...

StatAvg: Mitigating Data Heterogeneity in Federated Learning for Intrusion Detection Systems

Pavlos S. Bouzinis, Panagiotis Radoglou-Grammatikis · 2025

IEEE Transactions on Network and Se...

DA-FL: Blockchain Empowered Secure and Private Federated Learning With Anonymous Authentication

Hu Xiong, Yaxin Zhao · 2025

IEEE Transactions on Reliability

A Survey on Trustworthy Edge Intelligence: From Security and Reliability to Transparency and Sustainability

Xiaojie Wang, Beibei Wang · 2025

IEEE Communications Surveys & T...

Secure and Trustworthy Open Radio Access Network (O-RAN) Optimization: A Zero-Trust and Federated Learning Framework for 6G Networks

Mohammed El-Hajj · 2025

Future Internet

Federated Learning for 6G Networks: Navigating Privacy Benefits and Challenges

Chamara Sandeepa, Engin Zeydan · 2025

IEEE Open Journal of the Communicat...

Overview of AI and communication for 6G network: fundamentals, challenges, and future research opportunities

Qimei Cui, Xiaohu You · 2025

Science China Information Sciences

FedMedSecure: federated few-shot learning with cross-attention mechanisms and explainable AI for collaborative healthcare cybersecurity

Mohammed Tawfik, Ashraf A. Abu-Ein · 2025

Scientific Reports

Deep Learning and Federated Learning in Breast Cancer Screening and Diagnosis: A Systematic Review

Alexandru Ciobotaru, Cosmina Corches · 2025

IEEE Access

Metrics

1,971

Citations

38

References

Details

Published: Jan 01, 2020
Vol/Issue: 15
Pages: 3454-3469
License: View

Authors

K

Kang Wei

School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China

J

Jun Li

School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China

M

Ming Ding

CSIRO Data61, Sydney, NSW, Australia

C

Chuan Ma

School of Electrical and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China

H

Howard H. Yang

Singapore University of Technology and Design, Singapore

F

Farhad Farokhi

CSIRO’s Data61, Melbourne, VIC, Australia

S

Shi Jin

National Mobile Communications Research Laboratory, Southeast University, Nanjing, China

T

Tony Q. S. Quek

Singapore University of Technology and Design, Singapore

H

H. Vincent Poor

Department of Electrical Engineering, Princeton University, Princeton, NJ

Funding

National Natural Science Foundation of China Award: 61872184

National Key Research and Development Program of China Award: 2018YFB1004800

U.S. National Science Foundation Award: CCF-1908308

SUTD Growth Plan Grant for AI

Princeton Center for Statistics and Machine Learning under a Data X Grant

Cite This Article

Kang Wei, Jun Li, Ming Ding, et al. (2020). Federated Learning With Differential Privacy: Algorithms and Performance Analysis. IEEE Transactions on Information Forensics and Security, 15, 3454-3469. https://doi.org/10.1109/tifs.2020.2988575

Federated Learning With Differential Privacy: Algorithms and Performance Analysis

You May Also Like