mlsanityData to 14 Oct 2026

Vertical Federated Unlearning via Backdoor Certification

arXiv 2412.11476 ↗First posted 16 Dec 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets with identical sample identifiers but diverse attributes. Recent privacy regulations emphasize an individual's right to be forgotten, which necessitates the ability for models to unlearn specific training data. The primary challenge is to develop a mechanism to eliminate the influence of a specific client from a model without erasing all relevant data from other clients. Our research investigates the removal of a single client's contribution within the VFL framework. We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions. This approach seeks to optimize model performance using gradient ascent, guided by a pre-defined constrained model. We also introduce a backdoor mechanism to verify the effectiveness of the unlearning procedure. Our method avoids fully accessing the initial training data and avoids storing parameter updates. Empirical evidence shows that the results align closely with those achieved by retraining from scratch. Utilizing gradient ascent, our unlearning approach addresses key challenges in VFL, laying the groundwork for future advancements in this domain. All the code and implementations related to this paper are publicly available at https://github.com/mengde-han/VFL-unlearn.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

30 of 51 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  4. 2019Machine Unlearningcited by 1,061
  5. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  6. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  7. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 371
  8. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 311
  9. 2018Distributed learning of deep neural network over multiple agentscited by 279
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  11. 2021Fast Yet Effective Machine Unlearningcited by 217
  12. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
18 more
  1. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  2. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 171
  3. 2022Zero-Shot Machine Unlearningcited by 133
  4. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  5. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 95
  6. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  7. 2019Measure Contribution of Participants in Federated Learningcited by 79
  8. 2022Federated Unlearning with Knowledge Distillationcited by 73
  9. 2022Federated Unlearning for On-Device Recommendationcited by 43
  10. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 40
  11. 2021FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspectivecited by 36
  12. 2020Federated Unlearningcited by 29
  13. 2020More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligencecited by 23
  14. 2022FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learningcited by 23
  15. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 18
  16. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearningcited by 16
  17. 2023FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learningcited by 15
  18. 2023The Dark Side of Explanations: Poisoning Recommender Systems with Counterfactual Examplescited by 7

Built on by

Cited by year

Citing papers per year: 2025: 6.

6 papers.

  1. 2025Towards Reliable Forgetting: A Survey on Machine Unlearning Verificationcited by 8
  2. 2025How Secure is Forgetting? Linking Machine Unlearning to Machine Learning Attackscited by 4
  3. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearningcited by 1
  4. 2025REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Featurecited by 1
  5. 2025Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learningcited by 1
  6. 2025FedSGT: Exact Federated Unlearning via Sequential Group-based Trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning
  2. 2026Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
  3. 2023SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning
  4. 2025Unlearning Clients, Features and Samples in Vertical Federated Learning
  5. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning
  6. 2023BadVFL: Backdoor Attacks in Vertical Federated Learning
  7. 2024Federated Unlearning with Gradient Descent and Conflict Mitigation
  8. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics