mlsanityData to 14 Oct 2026

Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentation

arXiv 2208.10553 ↗First posted 22 Aug 2022cs.CV cs.CR cs.DCcited by 4

Not on the map. Why?

Abstract (arXiv)

Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows institutes with complementary features or images for a shared set of patients to jointly develop more robust and generalizable models. In this work, we propose "Split-U-Net" and successfully apply SL for collaborative biomedical image segmentation. Nonetheless, SL requires the exchanging of intermediate activation maps and gradients to allow training models across different feature spaces, which might leak data and raise privacy concerns. Therefore, we also quantify the amount of data leakage in common SL scenarios for biomedical image segmentation and provide ways to counteract such leakage by applying appropriate defense strategies.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 22 Aug 2022.

Builds on

21 of 33 references.

References · 21

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
  4. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  5. 2020The Future of Digital Health with Federated Learningcited by 633
  6. 2021The Medical Segmentation Decathloncited by 628
  7. 2019Federated Machine Learning: Concept and Applicationscited by 412
  8. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  9. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 373
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  11. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  12. 2018Distributed learning of deep neural network over multiple agentscited by 279
9 more
  1. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  2. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  3. 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 77
  4. 2019Split Learning for collaborative deep learning in healthcarecited by 73
  5. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  6. 2022Do Gradient Inversion Attacks Make Federated Learning Unsafe?cited by 44
  7. 2020Local Differential Privacy and Its Applications: A Comprehensive Surveycited by 41
  8. 2020Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learningcited by 12
  9. 2022Feasibility Study of Multi-Site Split Learning for Privacy-Preserving Medical Systems under Data Imbalance Constraints in COVID-19, X-Ray, and Cholesterol Datasetcited by 4

Built on by

Cited by year

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

4 papers.

  1. 2022Robust Split Federated Learning for U-shaped Medical Image Networkscited by 11
  2. 2023Recent Methodological Advances in Federated Learning for Healthcarecited by 11
  3. 2025A Taxonomy of Attacks and Defenses in Split Learningcited by 2
  4. 2024TabVFL: Improving Latent Representation in Vertical Federated Learningcited by 1