mlsanityData to 7 Oct 2026

CryptoNAS: Private Inference on a ReLU Budget

arXiv 2006.08733 ↗First posted 15 Jun 2020cs.LG cs.CR stat.MLcited by 40

Not on the map. Why?

Abstract (arXiv)

Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inputs. Recently, researchers have adapted cryptographic techniques to show PI is possible, however all solutions increase inference latency beyond practical limits. This paper makes the observation that existing models are ill-suited for PI and proposes a novel NAS method, named CryptoNAS, for finding and tailoring models to the needs of PI. The key insight is that in PI operator latency cost are non-linear operations (e.g., ReLU) dominate latency, while linear layers become effectively free. We develop the idea of a ReLU budget as a proxy for inference latency and use CryptoNAS to build models that maximize accuracy within a given budget. CryptoNAS improves accuracy by 3.4% and latency by 2.4x over the state-of-the-art.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 12; 2024: 8; 2025: 2; 2026: 3.

40 papers.

Sort:

  1. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  2. 2022Selective Network Linearization for Efficient Private Inferencecited by 31
  3. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  4. 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 26
  5. 2023Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inferencecited by 20
  6. 2022MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attentioncited by 19
  7. 2021Circa: Stochastic ReLUs for Private Deep Learningcited by 16
  8. 2021Sphynx: ReLU-Efficient Network Design for Private Inferencecited by 15
  9. 2024AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computingcited by 15
  10. 2021Layer Folding: Neural Network Depth Reduction using Activation Linearizationcited by 14
  11. 2021Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learningcited by 14
  12. 2022AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inferencecited by 14
28 more
  1. 2023RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inferencecited by 12
  2. 2022CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inferencecited by 10
  3. 2022zPROBE: Zero Peek Robustness Checks for Federated Learningcited by 6
  4. 2022Private and Reliable Neural Network Inferencecited by 6
  5. 2023Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryptioncited by 5
  6. 2024MPC-Minimized Secure LLM Inferencecited by 5
  7. 2022RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for low latency IoT systemscited by 4
  8. 2023Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inferencecited by 4
  9. 2023PriViT: Vision Transformers for Fast Private Inferencecited by 4
  10. 2022Efficient ML Models for Practical Secure Inferencecited by 2
  11. 2022PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inferencecited by 2
  12. 2023Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Taskscited by 2
  13. 2024Disparate Impact on Group Accuracy of Linearization for Private Inferencecited by 2
  14. 2022Efficient Deep Learning Using Non-Volatile Memory Technologycited by 1
  15. 2023Securing Neural Networks with Knapsack Optimizationcited by 1
  16. 2023Towards Fast and Scalable Private Inferencecited by 1
  17. 2023Compact: Approximating Complex Activation Functions for Secure Computationcited by 1
  18. 2024DCT-CryptoNets: Scaling Private Inference in the Frequency Domaincited by 1
  19. 2024PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimizationcited by 1
  20. 2024TruncFormer: Private LLM Inference Using Only Truncationscited by 1
  21. 2026ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hourcited by 1
  22. 2023Regularized PolyKervNets: Optimizing Expressiveness and Efficiency for Private Inference in Deep Neural Networkscited by 0
  23. 2024Linearizing Models for Efficient yet Robust Private Inferencecited by 0
  24. 2024xMLP: Revolutionizing Private Inference with Exclusive Square Activationcited by 0
  25. 2025Coordinate Descent for Network Linearizationcited by 0
  26. 2025DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inferencecited by 0
  27. 2026PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryptioncited by 0
  28. 2026HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptationcited by 0