mlsanityData to 14 Oct 2026

Efficient passive membership inference attack in federated learning

arXiv 2111.00430 ↗First posted 31 Oct 2021cs.LG cs.CR cs.DCcited by 16

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

Abstract (arXiv)

In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. However, recent work shows that client's private information can still be disclosed to an adversary who just eavesdrops the messages exchanged between the client and the server. For example, the adversary can infer whether the client owns a specific data instance, which is called a passive membership inference attack. In this paper, we propose a new passive inference attack that requires much less computation power and memory than existing methods. Our empirical results show that our attack achieves a higher accuracy on CIFAR100 dataset (more than 4 percentage points) with three orders of magnitude less memory space and five orders of magnitude less calculations.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 12 of its 17 references that are in the map. First posted on arXiv 31 Oct 2021.

Builds on

12 of 17 references.

References · 12

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2019Deep Leakage from Gradientscited by 1,021
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  8. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  10. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  11. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 130
  12. 2020Data and Model Dependencies of Membership Inference Attackcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 6; 2025: 2; 2026: 3.

16 papers.

Sort:

By area:

  1. 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 31
  2. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  3. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  4. 2024FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learningcited by 12
  5. 2022PPA: Preference Profiling Attack Against Federated Learningcited by 9
  6. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  7. 2022Towards Sparsified Federated Neuroimaging Models via Weight Pruningcited by 4
  8. 2024Low-Cost Privacy-Preserving Decentralized Learningcited by 4
  9. 2024Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learningcited by 3
  10. 2023RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defensecited by 2
  11. 2023Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddingscited by 1
  12. 2024Privacy-Preserving Heterogeneous Federated Learning for Sensitive Healthcare Datacited by 1
4 more
  1. 2026SoK: Challenges in Tabular Membership Inference Attackscited by 1
  2. 2026ERIS: Enhancing the Privacy-Utility-Scalability Trade-Off in Federated Learning via Federated Shard Aggregationcited by 1
  3. 2025An Efficient Gradient-Based Inference Attack for Federated Learningcited by 0
  4. 2026A Data-Free Membership Inference Attack on Federated Learning in Hardware Assurancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
  2. 2025Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
  3. 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
  4. 2023Active Membership Inference Attack under Local Differential Privacy in Federated Learning
  5. 2024Membership Information Leakage in Federated Contrastive Learning
  6. 2026United We Defend: Collaborative Membership Inference Defenses in Federated Learning
  7. 2026Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning Models
  8. 2021Securing Federated Learning: A Covert Communication-based Approach