TY - JOUR
T1 - GrCol-PPFL
T2 - User-Based Group Collaborative Federated Learning Privacy Protection Framework
AU - Cheng, Jieren
AU - Liu, Zhenhao
AU - Shi, Yiming
AU - Luo, Ping
AU - Sheng, Victor S.
N1 - Publisher Copyright:
© 2023 Tech Science Press. All rights reserved.
PY - 2023
Y1 - 2023
N2 - With the increasing number of smart devices and the development of machine learning technology, the value of users’ personal data is becoming more and more important. Based on the premise of protecting users’ personal privacy data, federated learning (FL) uses data stored on edge devices to realize training tasks by contributing training model parameters without revealing the original data. However, since FL can still leak the user’s original data by exchanging gradient information. The existing privacy protection strategy will increase the uplink time due to encryption measures. It is a huge challenge in terms of communication. When there are a large number of devices, the privacy protection cost of the system is higher. Based on these issues, we propose a privacy-preserving scheme of user-based group collaborative federated learning (GrCol-PPFL). Our scheme primarily divides participants into several groups and each group communicates in a chained transmission mechanism. All groups work in parallel at the same time. The server distributes a random parameter with the same dimension as the model parameter for each participant as a mask for the model parameter. We use the public datasets of modified national institute of standards and technology database (MNIST) to test the model accuracy. The experimental results show that GrCol-PPFL not only ensures the accuracy of the model, but also ensures the security of the user’s original data when users collude with each other. Finally, through numerical experiments, we show that by changing the number of groups, we can find the optimal number of groups that reduces the uplink consumption time.
AB - With the increasing number of smart devices and the development of machine learning technology, the value of users’ personal data is becoming more and more important. Based on the premise of protecting users’ personal privacy data, federated learning (FL) uses data stored on edge devices to realize training tasks by contributing training model parameters without revealing the original data. However, since FL can still leak the user’s original data by exchanging gradient information. The existing privacy protection strategy will increase the uplink time due to encryption measures. It is a huge challenge in terms of communication. When there are a large number of devices, the privacy protection cost of the system is higher. Based on these issues, we propose a privacy-preserving scheme of user-based group collaborative federated learning (GrCol-PPFL). Our scheme primarily divides participants into several groups and each group communicates in a chained transmission mechanism. All groups work in parallel at the same time. The server distributes a random parameter with the same dimension as the model parameter for each participant as a mask for the model parameter. We use the public datasets of modified national institute of standards and technology database (MNIST) to test the model accuracy. The experimental results show that GrCol-PPFL not only ensures the accuracy of the model, but also ensures the security of the user’s original data when users collude with each other. Finally, through numerical experiments, we show that by changing the number of groups, we can find the optimal number of groups that reduces the uplink consumption time.
KW - Federated learning
KW - privacy protection
KW - uplink consumption time
UR - http://www.scopus.com/inward/record.url?scp=85139791919&partnerID=8YFLogxK
U2 - 10.32604/cmc.2023.032758
DO - 10.32604/cmc.2023.032758
M3 - Article
AN - SCOPUS:85139791919
SN - 1546-2218
VL - 74
SP - 1923
EP - 1939
JO - Computers, Materials and Continua
JF - Computers, Materials and Continua
IS - 1
ER -