• Login
    View Item 
    •   Shocker Open Access Repository Home
    • Engineering
    • Electrical Engineering and Computer Science
    • EECS Faculty Scholarship
    • EECS Research Publications
    • View Item
    •   Shocker Open Access Repository Home
    • Engineering
    • Electrical Engineering and Computer Science
    • EECS Faculty Scholarship
    • EECS Research Publications
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Performance evaluation of a differentially-private neural network for cloud computing

    Date
    2018-12
    Author
    Hoefer, Nathaniel D.
    Salinas Monroy, Sergio A.
    Metadata
    Show full item record
    Citation
    N. D. Hoefer and S. A. Salinas Monroy, "Performance Evaluation of a Differentially-private Neural Network for Cloud Computing," 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 2018, pp. 2542-2545
    Abstract
    Due to the large computational cost of data classification using deep learning, resource-limited devices, e.g., smart phones, PCs, etc., offload their classification tasks to a cloud server, which offers extensive hardware resources. Unfortunately, since the cloud is an untrusted third-party, users may be reluctant to share their private data with the cloud for data classification. Differential privacy has been proposed as a way of securely classifying data at the cloud using deep learning. In this approach, users conceal their data before uploading it to the cloud using a local obfuscation deep learning model, which is based on a data classification model hosted by the cloud. However, as the obfuscation model assumes that the pre-trained model at the cloud is static, it leads to significant performance degradation under realistic classification models that are constantly being updated. In this paper, we investigate the performance of differentially-private data classification under a dynamic pre-trained model, and a constant obfuscation model. We find that the classification performance decreases as the pre-trained model evolves. We then investigate the classification performance under an obfuscation model that is updated alongside the pre-trained model. We find that with a modest computational effort the obfuscation model can be updated to significantly improve the classification performance. under a dynamic pre-trained model.
    Description
    Click on the DOI link to access the article (may not be free).
    URI
    https://doi.org/10.1109/BigData.2018.8622545
    http://hdl.handle.net/10057/16003
    Collections
    • EECS Research Publications

    Browse

    All of Shocker Open Access RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsBy TypeThis CollectionBy Issue DateAuthorsTitlesSubjectsBy Type

    My Account

    LoginRegister

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    DSpace software copyright © 2002-2021  DuraSpace
    Contact Us | Send Feedback
    DSpace Express is a service operated by 
    Atmire NV