Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 18, Issue 5, Pages 3316-3326Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3036166
Keywords
Big data; federated learning (FL); industrial Internet of Things (IoT); privacy-preserving; verifiable
Categories
Funding
- National Natural Science Foundation of China [62072239, 61941116, 62002167]
- Fundamental Research Funds for the Central Universities [30920021129]
- Jiangsu Key Laboratory of Big Data Security & Intelligent Processing under Grant NJUPT [BDSIP1909]
- Open Foundation of the State Key Laboratory of Information Security of China [2020-MS-01]
Ask authors/readers for more resources
This article proposes VFL, a verifiable federated learning approach with privacy-preserving for big data in industrial IoT. By using Lagrange interpolation for verifying the aggregated gradients and employing blinding technology to protect the privacy gradients, VFL achieves high accuracy and efficiency while preserving privacy.
Due to the strong analytical ability of big data, deep learning has been widely applied to model on the collected data in industrial Internet of Things (IoT). However, for privacy issues, traditional data-gathering centralized learning is not applicable to industrial scenarios sensitive to training sets, such as face recognition and medical systems. Recently, federated learning has received widespread attention, since it trains a model by only sharing gradients without accessing training sets. But existing research works reveal that the shared gradient still retains the sensitive information of the training set. Even worse, a malicious aggregation server may return forged aggregated gradients. In this article, we propose the VFL, a verifiable federated learning with privacy-preserving for big data in industrial IoT. Specifically, we use Lagrange interpolation to elaborately set interpolation points for verifying the correctness of the aggregated gradients. Compared with existing schemes, the verification overhead of VFL remains constant regardless of the number of participants. Moreover, we employ the blinding technology to protect the privacy of the privacy gradients. If no more than n-2 of n participants collude with the aggregation server, VFL could guarantee the encrypted gradients of other participants not being inverted. Experimental evaluations corroborate the practical performance of the presented VFL with high accuracy and efficiency.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available