MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference

Link:
Autor/in:
Verlag/Körperschaft:
Association for Computing Machinery (ACM)
Erscheinungsjahr:
2020
Medientyp:
Text
Schlagworte:
  • Particle Accelerators
  • RRAM
  • TOPS
  • Algorithms
  • Computer Vision
  • Models
  • Particle Accelerators
  • RRAM
  • TOPS
  • Algorithms
  • Computer Vision
  • Models
Beschreibung:
  • We present an extended abstract of MP2ML, a machine learning framework which integrates Intel nGraph-HE, a homomorphic encryption (HE) framework, and the secure two-party computation framework ABY, to enable data scientists to perform private inference of deep learning (DL) models trained using popular frameworks such as TensorFlow at the push of a button. We benchmark MP2ML on the CryptoNets network with ReLU activations, on which it achieves a throughput of 33.3 images/s and an accuracy of 98.6%. This throughput matches the previous state-of-The-Art frameworks.
Lizenz:
  • info:eu-repo/semantics/closedAccess
Quellsystem:
Forschungsinformationssystem der UHH

Interne Metadaten
Quelldatensatz
oai:www.edit.fis.uni-hamburg.de:publications/9c04e6da-625a-4641-89de-967dab2a0020