mlsanityData to 7 Oct 2026

ExPLoit: Extracting Private Labels in Split Learning

arXiv 2112.01299 ↗First posted 25 Nov 2021cs.CR cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Split learning is a popular technique used for vertical federated learning (VFL), where the goal is to jointly train a model on the private input and label data held by two parties. This technique uses a split-model, trained end-to-end, by exchanging the intermediate representations (IR) of the inputs and gradients of the IR between the two parties. We propose ExPLoit - a label-leakage attack that allows an adversarial input-owner to extract the private labels of the label-owner during split-learning. ExPLoit frames the attack as a supervised learning problem by using a novel loss function that combines gradient-matching and several regularization terms developed using key properties of the dataset and models. Our evaluations show that ExPLoit can uncover the private labels with near-perfect accuracy of up to 99.96%. Our findings underscore the need for better training techniques for VFL.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 25 Nov 2021.

Builds on

12 of 33 references.

References · 12

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2019Deep Leakage from Gradientscited by 1,004
  4. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  5. 2018Distributed learning of deep neural network over multiple agentscited by 277
  6. 2021Deep Learning with Label Differential Privacycited by 113
  7. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  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. 2019A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regressioncited by 37
  11. 2021Practical Defences Against Model Inversion Attacks for Split Neural Networkscited by 29
  12. 2018Reacting to Variations in Product Demand: An Application for Conversion Rate (CR) Prediction in Sponsored Searchcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 2; 2025: 5; 2026: 4.

15 papers.

Sort:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  2. 2022Similarity-based Label Inference Attack against Training and Inference of Split Learningcited by 15
  3. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  4. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  5. 2025SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)cited by 7
  6. 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
  7. 2022Protecting Split Learning by Potential Energy Losscited by 3
  8. 2025A Taxonomy of Attacks and Defenses in Split Learningcited by 1
  9. 2025A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraintscited by 1
  10. 2025Oops!... They Stole it Again: Attacks on Split Learningcited by 1
  11. 2026The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Modelscited by 1
  12. 2025Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigmscited by 0
3 more
  1. 2026Information Hidden in Gradients of Regression with Target Noisecited by 0
  2. 2026LEA: Label Enumeration Attack in Vertical Federated Learningcited by 0
  3. 2026Revisiting Label Inference Attacks in Vertical Federated Learning: Why They Are Vulnerable and How to Defendcited by 0