mlsanityData to 13 Oct 2026

PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization

arXiv 2410.09531 ↗First posted 12 Oct 2024cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Private deep neural network (DNN) inference based on secure two-party computation (2PC) enables secure privacy protection for both the server and the client. However, existing secure 2PC frameworks suffer from a high inference latency due to enormous communication. As the communication of both linear and non-linear DNN layers reduces with the bit widths of weight and activation, in this paper, we propose PrivQuant, a framework that jointly optimizes the 2PC-based quantized inference protocols and the network quantization algorithm, enabling communication-efficient private inference. PrivQuant proposes DNN architecture-aware optimizations for the 2PC protocols for communication-intensive quantized operators and conducts graph-level operator fusion for communication reduction. Moreover, PrivQuant also develops a communication-aware mixed precision quantization algorithm to improve inference efficiency while maintaining high accuracy. The network/protocol co-optimization enables PrivQuant to outperform prior-art 2PC frameworks. With extensive experiments, we demonstrate PrivQuant reduces communication by 11×, 2.5× and~ 2.8×, which results in 8.7×, 1.8× ~ and~ 2.4× latency reduction compared with SiRNN, COINN, and CoPriv, respectively.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 23 of its 44 references that are in the map. First posted on arXiv 12 Oct 2024.

Builds on

23 of 44 references.

References · 23

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,170
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,882
  3. 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
  4. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 518
  5. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  6. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 399
  7. 2023A Survey on Model Compression for Large Language Modelscited by 268
  8. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  9. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 125
  10. 2020CrypTFlow2: Practical 2-Party Secure Inferencecited by 82
  11. 2022MPCFormer: fast, performant and private Transformer inference with MPCcited by 68
  12. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
11 more
  1. 2019CrypTFlow: Secure TensorFlow Inferencecited by 61
  2. 2020FracBits: Mixed Precision Quantization via Fractional Bit-Widthscited by 55
  3. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  4. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  5. 2020CryptoNAS: Private Inference on a ReLU Budgetcited by 40
  6. 2022Selective Network Linearization for Efficient Private Inferencecited by 31
  7. 2021SIRNN: A Math Library for Secure RNN Inferencecited by 28
  8. 2021Generalizable Mixed-Precision Quantization via Attribution Rank Preservationcited by 11
  9. 2021GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networkscited by 10
  10. 2023CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inferencecited by 6
  11. 2023Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inferencecited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inference
  2. 2025Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
  3. 2025DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
  4. 2025Privacy-Preserving Inference for Quantized BERT Models
  5. 2025SecONNds: Secure Outsourced Neural Network Inference on ImageNet
  6. 2024FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference
  7. 2023Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning
  8. 2025CipherPrune: Efficient and Scalable Private Transformer Inference