mlsanityData to 7 Oct 2026

RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference

arXiv 2302.02292 ↗First posted 5 Feb 2023cs.CR cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

The proliferation of deep learning (DL) has led to the emergence of privacy and security concerns. To address these issues, secure Two-party computation (2PC) has been proposed as a means of enabling privacy-preserving DL computation. However, in practice, 2PC methods often incur high computation and communication overhead, which can impede their use in large-scale systems. To address this challenge, we introduce RRNet, a systematic framework that aims to jointly reduce the overhead of MPC comparison protocols and accelerate computation through hardware acceleration. Our approach integrates the hardware latency of cryptographic building blocks into the DNN loss function, resulting in improved energy efficiency, accuracy, and security guarantees. Furthermore, we propose a cryptographic hardware scheduler and corresponding performance model for Field Programmable Gate Arrays (FPGAs) to further enhance the efficiency of our framework. Experiments show RRNet achieved a much higher ReLU reduction performance than all SOTA works on CIFAR-10 dataset.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 5 Feb 2023.

Builds on

25 of 43 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  5. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  6. 2022Brain Network Transformercited by 92
  7. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 66
  8. 2019CrypTFlow: Secure TensorFlow Inferencecited by 61
  9. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  10. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  11. 2020Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Taskscited by 43
  12. 2020CryptoNAS: Private Inference on a ReLU Budgetcited by 40
13 more
  1. 2022Federated Contrastive Learning for Volumetric Medical Image Segmentationcited by 32
  2. 2022Selective Network Linearization for Efficient Private Inferencecited by 31
  3. 2020Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruningcited by 24
  4. 2021Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integrationcited by 21
  5. 2022Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learningcited by 21
  6. 2022A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipeliningcited by 21
  7. 2020Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devicescited by 19
  8. 2022Towards Sparsification of Graph Neural Networkscited by 18
  9. 2022Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-offcited by 15
  10. 2022An Accelerated Doubly Stochastic Gradient Method with Faster Explicit Model Identificationcited by 14
  11. 2022An Automatic and Efficient BERT Pruning for Edge AI Systemscited by 13
  12. 2021Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AIcited by 10
  13. 2021RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Searchcited by 8

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 8.

12 papers.

  1. 2024Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitatecited by 46
  2. 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 26
  3. 2023MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Trainingcited by 25
  4. 2024Predict Click-Through Rates with Deep Interest Network Model in E-commerce Advertisingcited by 10
  5. 2024Optimizing Search Advertising Strategies: Integrating Reinforcement Learning with Generalized Second-Price Auctions for Enhanced Ad Ranking and Biddingcited by 9
  6. 2024DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Modelcited by 8
  7. 2023QuMoS: A Framework for Preserving Security of Quantum Machine Learning Modelcited by 5
  8. 2024PristiQ: A Co-Design Framework for Preserving Data Security of Quantum Learning in the Cloudcited by 5
  9. 2024MPC-Minimized Secure LLM Inferencecited by 5
  10. 2023PriViT: Vision Transformers for Fast Private Inferencecited by 4
  11. 2024Key Information Retrieval to Classify the Unstructured Data Content of Preferential Trade Agreementscited by 1
  12. 2024International Trade Flow Prediction with Bilateral Trade Provisionscited by 0