mlsanityData to 13 Oct 2026

Mutual Information Regularization for Vertical Federated Learning

arXiv 2301.01142 ↗First posted 1 Jan 2023cs.LGcited by 3

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Vertical Federated Learning (VFL) is widely utilized in real-world applications to enable collaborative learning while protecting data privacy and safety. However, previous works show that parties without labels (passive parties) in VFL can infer the sensitive label information owned by the party with labels (active party) or execute backdoor attacks to VFL. Meanwhile, active party can also infer sensitive feature information from passive party. All these pose new privacy and security challenges to VFL systems. We propose a new general defense method which limits the mutual information between private raw data, including both features and labels, and intermediate outputs to achieve a better trade-off between model utility and privacy. We term this defense Mutual Information Regularization Defense (MID). We theoretically and experimentally testify the effectiveness of our MID method in defending existing attacks in VFL, including label inference attacks, backdoor attacks and feature reconstruction attacks.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 21 of its 45 references that are in the map. First posted on arXiv 1 Jan 2023.

Builds on

21 of 45 references.

References · 21

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  2. 2019Deep Leakage from Gradientscited by 1,017
  3. 2016Deep Variational Information Bottleneckcited by 924
  4. 2015Deep Learning and the Information Bottleneck Principlecited by 796
  5. 2018How To Backdoor Federated Learningcited by 764
  6. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 380
  8. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  9. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  10. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
  11. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  12. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
9 more
  1. 2020InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspectivecited by 92
  2. 2021Label Leakage and Protection in Two-party Split Learningcited by 90
  3. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  4. 2020Improving Robustness to Model Inversion Attacks via Mutual Information Regularizationcited by 52
  5. 2020Privacy-preserving Collaborative Learning with Automatic Transformation Searchcited by 31
  6. 2020Backdoor attacks and defenses in feature-partitioned collaborative learningcited by 30
  7. 2018Secure Federated Transfer Learningcited by 13
  8. 2022Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learningcited by 13
  9. 2022Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyondcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023VFLAIR: A Research Library and Benchmark for Vertical Federated Learningcited by 8
  2. 2023PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Informationcited by 4
  3. 2025VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Maskingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification
  2. 2021Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learning
  3. 2026Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
  4. 2023BadVFL: Backdoor Attacks in Vertical Federated Learning
  5. 2023Practical and General Backdoor Attacks against Vertical Federated Learning
  6. 2025Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning
  7. 2026Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning
  8. 2025HASSLE: A Self-Supervised Learning Enhanced Hijacking Attack on Vertical Federated Learning