Now showing items 1-1 of 1

    • Enabling homomorphically encrypted inference for large DNN models 

      Lloret Talavera, Guillermo; Jorda, Marc; Servat, Harald; Boemer, Fabian; Chauhan, Chetan; Tomishima, Shigeki; Shah, Nilesh N.; Peña, Antonio (Institute of Electrical and Electronics Engineers, 2021)
      Open Access
      The proliferation of machine learning services in the last few years has raised data privacy concerns. Homomorphic encryption (HE) enables inference using encrypted data but it incurs 100x-10,000x memory and runtime ...