Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference

Abstract

Homomorphic encryption enables arbitrary computation over data while it remains encrypted. This privacy-preserving feature is attractive for machine learning, but requires significant computational time due to the large overhead of the encryption scheme. We present Faster CryptoNets, a method for efficient encrypted inference using neural networks. We develop a pruning and quantization approach that leverages sparse representations in the underlying cryptosystem to accelerate inference. We derive an optimal approximation for popular activation functions that achieves maximally-sparse encodings and minimizes approximation error. We also show how privacy-safe training techniques can be used to reduce the overhead of encrypted inference for real-world datasets by leveraging transfer learning and differential privacy. Our experiments show that our method maintains competitive accuracy and achieves a significant speedup over previous methods. This work increases the viability of deep learning systems that use homomorphic encryption to protect user privacy.

References in corpus (10)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Deep Learning with Differential Privacy
• Deep Residual Learning for Image Recognition
• Stealing Machine Learning Models via Prediction APIs
• Rethinking the Inception Architecture for Computer Vision
• Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
• Learning Structured Sparsity in Deep Neural Networks
• Scalable Private Learning with PATE
• Faster arithmetic for number-theoretic transforms
• On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches

Cited by in corpus (28)

• XONN: XNOR-based Oblivious Deep Neural Network Inference
• PrivFT: Private and Fast Text Classification with Homomorphic Encryption
• HEAAN Demystified: Accelerating Fully Homomorphic Encryption Through Architecture-centric Analysis and Optimization
• Security and Privacy Issues in Deep Learning
• Secure Byzantine-Robust Machine Learning
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Enabling Homomorphically Encrypted Inference for Large DNN Models
• nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
• HEAX: An Architecture for Computing on Encrypted Data
• On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks
• Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs
• nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data
• CaRENets: Compact and Resource-Efficient CNN for Homomorphic Inference on Encrypted Medical Images
• Circa: Stochastic ReLUs for Private Deep Learning
• Towards Characterizing and Limiting Information Exposure in DNN Layers
• Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
• Popcorn: Paillier Meets Compression For Efficient Oblivious Neural Network Inference
• Partially Oblivious Neural Network Inference
• Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
• Efficient CNN Building Blocks for Encrypted Data
• Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption
• ArchNet: Data Hiding Model in Distributed Machine Learning System
• CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations
• ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition
• MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference
• GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks
• CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale
• Accelerating 2PC-based ML with Limited Trusted Hardware