Efficient and secure federated learning against backdoor attacks

Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differen...

Full description

Saved in:

Bibliographic Details
Main Authors:	MIAO, Yinbin, XIE, Rongpeng, LI, Xinghua, LIU, Zhiquan, CHOO, Kim-Kwang Raymond, DENG, Robert H.
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2024
Subjects:	Adaptation models Adaptive local differential privacy Artificial neural networks Backdoor attacks Compressive sensing Federated learning Gaussian noise Privacy Servers Training Information Security
Online Access:	https://ink.library.smu.edu.sg/sis_research/8660 https://ink.library.smu.edu.sg/context/sis_research/article/9663/viewcontent/Eff_Secure_FL_BackdoorAttacks_av.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-9663
record_format	dspace
spelling	sg-smu-ink.sis_research-96632024-11-08T08:05:02Z Efficient and secure federated learning against backdoor attacks MIAO, Yinbin XIE, Rongpeng LI, Xinghua LIU, Zhiquan CHOO, Kim-Kwang Raymond DENG, Robert H. Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differential Privacy (LDP) solutions can provide privacy protection to a certain extent, but these solutions still cannot achieve adaptive perturbation in DNN model. In addition, this kind of schemes cause high communication overheads due to the curse of dimensionality of DNN, and are naturally vulnerable to backdoor attacks due to the inherent distributed characteristic. To solve these issues, we propose an E fficient and S ecure F ederated L earning scheme (ESFL) against backdoor attacks by using adaptive LDP and compressive sensing. Formal security analysis proves that ESFL satisfies ϵ -LDP security. Extensive experiments using three datasets demonstrate that ESFL can solve the problems of traditional LDP-based FL schemes without a loss of model accuracy and efficiently resist the backdoor attacks. 2024-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8660 info:doi/10.1109/TDSC.2024.3354736 https://ink.library.smu.edu.sg/context/sis_research/article/9663/viewcontent/Eff_Secure_FL_BackdoorAttacks_av.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Adaptation models Adaptive local differential privacy Artificial neural networks Backdoor attacks Compressive sensing Federated learning Federated learning Gaussian noise Privacy Servers Training Information Security
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Adaptation models Adaptive local differential privacy Artificial neural networks Backdoor attacks Compressive sensing Federated learning Federated learning Gaussian noise Privacy Servers Training Information Security
spellingShingle	Adaptation models Adaptive local differential privacy Artificial neural networks Backdoor attacks Compressive sensing Federated learning Federated learning Gaussian noise Privacy Servers Training Information Security MIAO, Yinbin XIE, Rongpeng LI, Xinghua LIU, Zhiquan CHOO, Kim-Kwang Raymond DENG, Robert H. Efficient and secure federated learning against backdoor attacks
description	Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differential Privacy (LDP) solutions can provide privacy protection to a certain extent, but these solutions still cannot achieve adaptive perturbation in DNN model. In addition, this kind of schemes cause high communication overheads due to the curse of dimensionality of DNN, and are naturally vulnerable to backdoor attacks due to the inherent distributed characteristic. To solve these issues, we propose an E fficient and S ecure F ederated L earning scheme (ESFL) against backdoor attacks by using adaptive LDP and compressive sensing. Formal security analysis proves that ESFL satisfies ϵ -LDP security. Extensive experiments using three datasets demonstrate that ESFL can solve the problems of traditional LDP-based FL schemes without a loss of model accuracy and efficiently resist the backdoor attacks.
format	text
author	MIAO, Yinbin XIE, Rongpeng LI, Xinghua LIU, Zhiquan CHOO, Kim-Kwang Raymond DENG, Robert H.
author_facet	MIAO, Yinbin XIE, Rongpeng LI, Xinghua LIU, Zhiquan CHOO, Kim-Kwang Raymond DENG, Robert H.
author_sort	MIAO, Yinbin
title	Efficient and secure federated learning against backdoor attacks
title_short	Efficient and secure federated learning against backdoor attacks
title_full	Efficient and secure federated learning against backdoor attacks
title_fullStr	Efficient and secure federated learning against backdoor attacks
title_full_unstemmed	Efficient and secure federated learning against backdoor attacks
title_sort	efficient and secure federated learning against backdoor attacks
publisher	Institutional Knowledge at Singapore Management University
publishDate	2024
url	https://ink.library.smu.edu.sg/sis_research/8660 https://ink.library.smu.edu.sg/context/sis_research/article/9663/viewcontent/Eff_Secure_FL_BackdoorAttacks_av.pdf
_version_	1816859097966837760

Efficient and secure federated learning against backdoor attacks

Similar Items