mlsanityData to 7 Oct 2026

Differentially Private Label Protection in Split Learning

arXiv 2203.02073 ↗First posted 4 Mar 2022cs.LG cs.CR cs.DScited by 25

Not on the map. Why?

Abstract (arXiv)

Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attributes). The idea is that only intermediate computation results, rather than private features and labels, are shared between parties so that raw training data remains private. Nevertheless, recent works showed that the plaintext implementation of split learning suffers from severe privacy risks that a semi-honest adversary can easily reconstruct labels. In this work, we propose textsfTPSL (Transcript Private Split Learning), a generic gradient perturbation based split learning framework that provides provable differential privacy guarantee. Differential privacy is enforced on not only the model weights, but also the communicated messages in the distributed computation setting. Our experiments on large-scale real-world datasets demonstrate the robustness and effectiveness of textsfTPSL against label leakage attacks. We also find that textsfTPSL have a better utility-privacy trade-off than baselines.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

26 of 42 references.

References · 26

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2016Wide & Deep Learning for Recommender Systemscited by 745
  4. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  5. 2018Spectral Signatures in Backdoor Attackscited by 457
  6. 2019Federated Machine Learning: Concept and Applicationscited by 409
  7. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  8. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  9. 2018Distributed learning of deep neural network over multiple agentscited by 277
  10. 2018Scalable Private Learning with PATEcited by 266
  11. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 233
  12. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
14 more
  1. 2017Collecting Telemetry Data Privatelycited by 147
  2. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 122
  3. 2021Deep Learning with Label Differential Privacycited by 113
  4. 2014Preserving Statistical Validity in Adaptive Data Analysiscited by 102
  5. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  6. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  7. 2020Federated Accelerated Stochastic Gradient Descentcited by 85
  8. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  9. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  10. 2021Antipodes of Label Differential Privacy: PATE and ALIBIcited by 50
  11. 2020SplitNN-driven Vertical Partitioningcited by 42
  12. 2019A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regressioncited by 37
  13. 2020Hybrid Differentially Private Federated Learning on Vertically Partitioned Datacited by 22
  14. 2021Vertical Federated Learning without Revealing Intersection Membershipcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 9; 2024: 8; 2025: 3; 2026: 1.

25 papers.

Sort:

By area:

  1. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  2. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  3. 2023Split-and-Denoise: Protect large language model inference with local differential privacycited by 30
  4. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  5. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  6. 2022Differentially Private CutMix for Split Learning with Vision Transformercited by 13
  7. 2022Vertical Semi-Federated Learning for Efficient Online Advertisingcited by 12
  8. 2024SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimizationcited by 10
  9. 2023VFLAIR: A Research Library and Benchmark for Vertical Federated Learningcited by 8
  10. 2023Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiencycited by 8
  11. 2023Label Inference Attack against Split Learning under Regression Settingcited by 7
  12. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
13 more
  1. 2025SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)cited by 7
  2. 2022VFed-SSD: Towards Practical Vertical Federated Advertisingcited by 5
  3. 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
  4. 2023PFSL: Personalized & Fair Split Learning with Data & Label Privacy for thin clientscited by 3
  5. 2024Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMixcited by 2
  6. 2024LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscationcited by 1
  7. 2024S2NeRF: Privacy-preserving Training Framework for NeRFcited by 1
  8. 2025Oops!... They Stole it Again: Attacks on Split Learningcited by 1
  9. 2026The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Modelscited by 1
  10. 2023GAN-based Vertical Federated Learning for Label Protection in Binary Classificationcited by 0
  11. 2024FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscationcited by 0
  12. 2024On Differentially Private String Distancescited by 0
  13. 2025Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Maskingcited by 0