mlsanityData to 7 Oct 2026

Sphynx: ReLU-Efficient Network Design for Private Inference

arXiv 2106.11755 ↗First posted 17 Jun 2021cs.CR cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

The emergence of deep learning has been accompanied by privacy concerns surrounding users' data and service providers' models. We focus on private inference (PI), where the goal is to perform inference on a user's data sample using a service provider's model. Existing PI methods for deep networks enable cryptographically secure inference with little drop in functionality; however, they incur severe latency costs, primarily caused by non-linear network operations (such as ReLUs). This paper presents Sphynx, a ReLU-efficient network design method based on micro-search strategies for convolutional cell design. Sphynx achieves Pareto dominance over all existing private inference methods on CIFAR-100. We also design large-scale networks that support cryptographically private inference on Tiny-ImageNet and ImageNet.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

23 of 39 references.

References · 23

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  5. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  6. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  7. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  8. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  9. 2013Do Deep Nets Really Need to be Deep?cited by 466
  10. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  11. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  12. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
11 more
  1. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 258
  2. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 253
  3. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  4. 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
  5. 2019NAS evaluation is frustratingly hardcited by 69
  6. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  7. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  8. 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
  9. 2020Geometry-Aware Gradient Algorithms for Neural Architecture Searchcited by 40
  10. 2020CryptoNAS: Private Inference on a ReLU Budgetcited by 40
  11. 2019One-Shot Neural Architecture Search via Compressive Sensingcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 5; 2024: 4; 2025: 2.

15 papers.

Sort:

  1. 2022Selective Network Linearization for Efficient Private Inferencecited by 31
  2. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  3. 2022MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attentioncited by 19
  4. 2022AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inferencecited by 14
  5. 2024MPC-Minimized Secure LLM Inferencecited by 5
  6. 2023Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inferencecited by 4
  7. 2023PriViT: Vision Transformers for Fast Private Inferencecited by 4
  8. 2022Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inferencecited by 2
  9. 2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
  10. 2024HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inferencecited by 2
  11. 2023Towards Fast and Scalable Private Inferencecited by 1
  12. 2024TruncFormer: Private LLM Inference Using Only Truncationscited by 1
3 more
  1. 2025CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computationcited by 1
  2. 2024xMLP: Revolutionizing Private Inference with Exclusive Square Activationcited by 0
  3. 2025DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inferencecited by 0