SEALion: a Framework for Neural Network Inference on Encrypted Data

Abstract

We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives; the second implements a Keras-like syntax for training and inference with neural networks. Given a required level of security, a user is abstracted from the details of the encoding and the encryption scheme, allowing quick prototyping. We present two applications that exemplifying the extensibility of our proposal, which are also of independent interest: i) improving efficiency of neural network inference by an activity sparsifier and ii) transfer learning by querying a server-side Variational AutoEncoder that can handle encrypted data.

References in corpus (11)

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Semi-Supervised Learning with Deep Generative Models
• EMNIST: an extension of MNIST to handwritten letters
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• A generic framework for privacy preserving deep learning
• Learning Sparse Neural Networks through $L_0$ Regularization
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
• Private Machine Learning in TensorFlow using Secure Computation
• CHET: Compiler and Runtime for Homomorphic Evaluation of Tensor Programs

Cited by in corpus (9)

• SoK: Fully Homomorphic Encryption Compilers
• BlindFL: Vertical Federated Machine Learning without Peeking into Your Data
• HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
• Offline Model Guard: Secure and Private ML on Mobile Devices
• nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
• Enabling Homomorphically Encrypted Inference for Large DNN Models
• A General Purpose Transpiler for Fully Homomorphic Encryption
• SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation
• Partially Oblivious Neural Network Inference