Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs

Abstract

Deep Learning as a Service (DLaaS) stands as a promising solution for cloud-based inference applications. In this setting, the cloud has a pre-learned model whereas the user has samples on which she wants to run the model. The biggest concern with DLaaS is user privacy if the input samples are sensitive data. We provide here an efficient privacy-preserving system by employing high-end technologies such as Fully Homomorphic Encryption (FHE), Convolutional Neural Networks (CNNs) and Graphics Processing Units (GPUs). FHE, with its widely-known feature of computing on encrypted data, empowers a wide range of privacy-concerned applications. This comes at high cost as it requires enormous computing power. In this paper, we show how to accelerate the performance of running CNNs on encrypted data with GPUs. We evaluated two CNNs to classify homomorphically the MNIST and CIFAR-10 datasets. Our solution achieved a sufficient security level (> 80 bit) and reasonable classification accuracy (99%) and (77.55%) for MNIST and CIFAR-10, respectively. In terms of latency, we could classify an image in 5.16 seconds and 304.43 seconds for MNIST and CIFAR-10, respectively. Our system can also classify a batch of images (> 8,000) without extra overhead.

References in corpus (9)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Fractional Max-Pooling
• SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Execution
• CryptoDL: Deep Neural Networks over Encrypted Data
• XONN: XNOR-based Oblivious Deep Neural Network Inference
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
• Encrypted statistical machine learning: new privacy preserving methods

Cited by in corpus (6)

• The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research
• PrivFT: Private and Fast Text Classification with Homomorphic Encryption
• HEAAN Demystified: Accelerating Fully Homomorphic Encryption Through Architecture-centric Analysis and Optimization
• When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control
• A brief history on Homomorphic learning: A privacy-focused approach to machine learning
• Efficient Encrypted Inference on Ensembles of Decision Trees