Edge computing privacy protection method based on blockchain and federated learning
Aiming at the needs of edge computing for data privacy, the correctness of calculation results and the auditability of data processing, a privacy protection method for edge computing based on blockchain and federated learning was proposed, which can realize collaborative training with multiple devic...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2021-11-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021190/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539214013890560 |
|---|---|
| author | Chen FANG Yuanbo GUO Yifeng WANG Yongjin HU Jiali MA Han ZHANG Yangyang HU |
| author_facet | Chen FANG Yuanbo GUO Yifeng WANG Yongjin HU Jiali MA Han ZHANG Yangyang HU |
| author_sort | Chen FANG |
| collection | DOAJ |
| description | Aiming at the needs of edge computing for data privacy, the correctness of calculation results and the auditability of data processing, a privacy protection method for edge computing based on blockchain and federated learning was proposed, which can realize collaborative training with multiple devices at the edge of the network without a trusted environment and special hardware facilities.The blockchain was used to endow the edge computing with features such as tamper-proof and resistance to single-point-of-failure attacks, and the gradient verification and incentive mechanism were incorporated into the consensus protocol to encourage more local devices to honestly contribute computing power and data to the federated learning.For the potential privacy leakage problems caused by sharing model parameters, an adaptive differential privacy mechanism was designed to protect parameter privacy while reducing the impact of noise on the model accuracy, and moments accountant was used to accurately track the privacy loss during the training process.Experimental results show that the proposed method can resist 30% of poisoning attacks, and can achieve privacy protection with high model accuracy, and is suitable for edge computing scenarios that require high level of security and accuracy. |
| format | Article |
| id | doaj-art-8b82aa0a0f29423d80591c40cf9dd8e9 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2021-11-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-8b82aa0a0f29423d80591c40cf9dd8e92025-01-14T07:23:04ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2021-11-0142284059745804Edge computing privacy protection method based on blockchain and federated learningChen FANGYuanbo GUOYifeng WANGYongjin HUJiali MAHan ZHANGYangyang HUAiming at the needs of edge computing for data privacy, the correctness of calculation results and the auditability of data processing, a privacy protection method for edge computing based on blockchain and federated learning was proposed, which can realize collaborative training with multiple devices at the edge of the network without a trusted environment and special hardware facilities.The blockchain was used to endow the edge computing with features such as tamper-proof and resistance to single-point-of-failure attacks, and the gradient verification and incentive mechanism were incorporated into the consensus protocol to encourage more local devices to honestly contribute computing power and data to the federated learning.For the potential privacy leakage problems caused by sharing model parameters, an adaptive differential privacy mechanism was designed to protect parameter privacy while reducing the impact of noise on the model accuracy, and moments accountant was used to accurately track the privacy loss during the training process.Experimental results show that the proposed method can resist 30% of poisoning attacks, and can achieve privacy protection with high model accuracy, and is suitable for edge computing scenarios that require high level of security and accuracy.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021190/federated learningedge computingblockchainpoisoning attackprivacy preservation |
| spellingShingle | Chen FANG Yuanbo GUO Yifeng WANG Yongjin HU Jiali MA Han ZHANG Yangyang HU Edge computing privacy protection method based on blockchain and federated learning Tongxin xuebao federated learning edge computing blockchain poisoning attack privacy preservation |
| title | Edge computing privacy protection method based on blockchain and federated learning |
| title_full | Edge computing privacy protection method based on blockchain and federated learning |
| title_fullStr | Edge computing privacy protection method based on blockchain and federated learning |
| title_full_unstemmed | Edge computing privacy protection method based on blockchain and federated learning |
| title_short | Edge computing privacy protection method based on blockchain and federated learning |
| title_sort | edge computing privacy protection method based on blockchain and federated learning |
| topic | federated learning edge computing blockchain poisoning attack privacy preservation |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021190/ |
| work_keys_str_mv | AT chenfang edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning AT yuanboguo edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning AT yifengwang edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning AT yongjinhu edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning AT jialima edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning AT hanzhang edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning AT yangyanghu edgecomputingprivacyprotectionmethodbasedonblockchainandfederatedlearning |