nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

    Fabian Boemer
    Fabian Boemer
    Yixing Lao
    Yixing Lao
    Casimir Wierzynski
    Casimir Wierzynski

    Proceedings of the 16th ACM International Conference on Computing Frontiers, Volume abs/1810.10121, 2019.

    Cited by: 14|Bibtex|Views7|Links
    EI
    Keywords:
    deep learning homomorphic encryption intermediate representation

    Abstract:

    Homomorphic encryption (HE)---the ability to perform computation on encrypted data---is an attractive remedy to increasing concerns about data privacy in deep learning (DL). However, building DL models that operate on ciphertext is currently labor-intensive and requires simultaneous expertise in DL, cryptography, and software engineering....More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments