Oblivious Neural Network Predictions via MiniONN Transformations

Machine learning models hosted in a cloud service are increasingly popular but risk privacy: clients sending prediction requests to the service need to disclose potentially sensitive information. In this paper, we explore the problem of privacy-preserving predictions: after each prediction, the server learns nothing about clients' input and clients learn nothing about the model.

• AO
  Academy of Finland

  Award: 274951
• T
  Tekes