• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
Advanced Search
Jin Ge, Wei Xiaochao, Wei Senmao, Wang Hao. FPCBC: Federated Learning Privacy Preserving Classification System Based on Crowdsourcing Aggregation[J]. Journal of Computer Research and Development, 2022, 59(11): 2377-2394. DOI: 10.7544/issn1000-1239.20220528
Citation: Jin Ge, Wei Xiaochao, Wei Senmao, Wang Hao. FPCBC: Federated Learning Privacy Preserving Classification System Based on Crowdsourcing Aggregation[J]. Journal of Computer Research and Development, 2022, 59(11): 2377-2394. DOI: 10.7544/issn1000-1239.20220528

FPCBC: Federated Learning Privacy Preserving Classification System Based on Crowdsourcing Aggregation

Funds: This work was supported by the China Postdoctoral Science Foundation (2018M632712), the National Natural Science Foundation of China for Young Scientists (61802235), and the General Program of the National Natural Science Foundation of China (62071280).
More Information
  • Published Date: October 31, 2022
  • With the continuous increase of data assets from enterprises, governments and private individuals, the demand for classification applications such as images in the field of machine learning is also increasing. In order to meet various practical needs, the idea of cloud service deployment in machine learning as a service (MLAAS) has gradually become the mainstream. However, applications based on cloud services often bring serious data privacy and security leakage issues. FPCBC is a federated learning privacy-preserving classification system based on crowdsourcing aggregation. It crowdsources classification tasks to multiple edge participants and uses cloud computing to complete the whole process. However, instead of using the method of jointly training ideal models to obtain high-confidence classification results, we let the participants first train model based on limited local data and use the model to infer, and then we use mature algorithms to aggregate the inference results to obtain classification with higher accuracy. Importantly, users won’t leak any private data, which solves the privacy and security issues of traditional MLAAS. During the system implementation, we use homomorphic encryption to encrypt image data that requires machine learning inference; we also improve a crowdsourced federated learning classification algorithm, and implement the privacy-preserving computation of the entire system by introducing a dual-server mechanism. Experiments and performance analysis show that the system is feasible, the security degree of privacy protection has been significantly improved, and it is more suitable for application scenarios with high privacy and security requirements in real life.

Catalog

    Article views (475) PDF downloads (172) Cited by()
    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return