mlsanityData to 7 Oct 2026

Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction

arXiv 2206.04864 ↗First posted 10 Jun 2022cs.LG cs.CRcited by 11

Not on the map. Why?

Abstract (arXiv)

Split learning (SL) enables data privacy preservation by allowing clients to collaboratively train a deep learning model with the server without sharing raw data. However, SL still has limitations such as potential data privacy leakage and high computation at clients. In this study, we propose to binarize the SL local layers for faster computation (up to 17.5 times less forward-propagation time in both training and inference phases on mobile devices) and reduced memory usage (up to 32 times less memory and bandwidth requirements). More importantly, the binarized SL (B-SL) model can reduce privacy leakage from SL smashed data with merely a small degradation in model accuracy. To further enhance the privacy preservation, we also propose two novel approaches: 1) training with additional local leak loss and 2) applying differential privacy, which could be integrated separately or concurrently into the B-SL model. Experimental results with different datasets have affirmed the advantages of the B-SL models compared with several benchmark models. The effectiveness of B-SL models against feature-space hijacking attack (FSHA) is also illustrated. Our results have demonstrated B-SL models are promising for lightweight IoT/mobile applications with high privacy-preservation requirements such as mobile healthcare applications.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 28 of its 56 references that are in the map. First posted on arXiv 10 Jun 2022.

Builds on

28 of 56 references.

References · 28

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  5. 2016An overview of gradient descent optimization algorithmscited by 1,021
  6. 2019Deep Leakage from Gradientscited by 1,004
  7. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  9. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  10. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  11. 2018Distributed learning of deep neural network over multiple agentscited by 277
  12. 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 225
16 more
  1. 2020Binary Neural Networks: A Surveycited by 184
  2. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
  3. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 104
  4. 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 76
  5. 2020Privacy in Deep Learning: A Surveycited by 70
  6. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  7. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  8. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
  9. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  10. 2018No Peek: A Survey of private distributed deep learningcited by 30
  11. 2018Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloudcited by 28
  12. 2020Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networkscited by 15
  13. 2017Dropping Activation Outputs with Localized First-layer Deep Network for Enhancing User Privacy and Data Securitycited by 8
  14. 2022PPA: Preference Profiling Attack Against Federated Learningcited by 8
  15. 2019Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learningcited by 2
  16. 2021Can Differential Privacy Practically Protect Collaborative Deep Learning Inference for the Internet of Things?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 5; 2025: 2; 2026: 1.

11 papers.

  1. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  2. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  3. 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devicescited by 9
  4. 2023Secure Transformer Inference Protocolcited by 5
  5. 2024COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platformscited by 5
  6. 2024Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inferencecited by 2
  7. 2024Split Learning in Computer Vision for Semantic Segmentation Delay Minimizationcited by 2
  8. 2024Towards Secure and Private AI: A Framework for Decentralized Inferencecited by 1
  9. 2025ReinDSplit: Reinforced Dynamic Split Learning for Pest Recognition in Precision Agriculturecited by 0
  10. 2025Pigeon-SL: Robust Split Learning Framework for Edge Intelligence under Malicious Clientscited by 0
  11. 2026Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learningcited by 0