Encrypted Machine Learning

Encrypted Machine Learning is a computational framework that enables machine learning models to perform training and inference directly on encrypted data using homomorphic encryption, thereby preserving data privacy while maintaining the functionality of the learning algorithm.

183

Publications

11.2K

Citations

642

Authors

268

Institutions

Publications per year

2017–2026

158

Authors

642

  1. KL
    Kristin Lauter

    Microsoft (United States), United States

    6 publications · 2K citations

    6

    h-index

  2. JH
    Jung Hee Cheon

    Seoul National University, South Korea

    5 publications · 295 citations

    5

    h-index

  3. MG
    Mehdi Ghasemi

    University of Saskatchewan, Canada

    4 publications · 697 citations

    4

    h-index

  4. HT
    Hassan Takabi

    University of North Texas, United States

    4 publications · 697 citations

    4

    h-index

  5. EH
    Ehsan Hesamifard

    University of North Texas, United States

    4 publications · 697 citations

    4

    h-index

1–5 of 642

Venues

  1. arXiv (Cornell University)

    Repository · 22 publications · 1.1K citations

    16

    h-index

  2. IEEE Access

    12 publications · 587 citations

    12

    h-index

  3. IACR Cryptology ePrint Archive

    Repository · 8 publications · 201 citations

    8

    h-index

  4. EURASIP Journal on Information Security

    4 publications · 214 citations

    4

    h-index

  5. IEEE Internet of Things Journal

    3 publications · 359 citations

    3

    h-index

1–5