mlsanityData to 7 Oct 2026

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning

arXiv 2402.06289 ↗First posted 9 Feb 2024cs.LG cs.CRcited by 10

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

Abstract (arXiv)

Federated Learning (FL) is a promising approach for training machine learning models on decentralized data while preserving privacy. However, privacy risks, particularly Membership Inference Attacks (MIAs), which aim to determine whether a specific data point belongs to a target client's training set, remain a significant concern. Existing methods for implementing MIAs in FL primarily analyze updates from the target client, focusing on metrics such as loss, gradient norm, and gradient difference. However, these methods fail to leverage updates from non-target clients, potentially underutilizing available information. In this paper, we first formulate a one-tailed likelihood-ratio hypothesis test based on the likelihood of updates from non-target clients. Building upon this formulation, we introduce a three-step Membership Inference Attack (MIA) method, called FedMIA, which follows the "all for one"--leveraging updates from all clients across multiple communication rounds to enhance MIA effectiveness. Both theoretical analysis and extensive experimental results demonstrate that FedMIA outperforms existing MIAs in both classification and generative tasks. Additionally, it can be integrated as an extension to existing methods and is robust against various defense strategies, Non-IID data, and different federated structures. Our code is available in https://github.com/Liar-Mask/FedMIA.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 30 of its 54 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

30 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learning30 Sep
  2. 2022Subject Membership Inference Attacks in Federated Learning7 Jun
  3. 2021Efficient passive membership inference attack in federated learning31 Oct

Other references · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2019Deep Leakage from Gradientscited by 1,004
  7. 2021Membership Inference Attacks From First Principlescited by 839
  8. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  9. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  10. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  11. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  12. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
15 more
  1. 2019Federated Machine Learning: Concept and Applicationscited by 409
  2. 2020Label-Only Membership Inference Attackscited by 371
  3. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  4. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  5. 2018Distributed learning of deep neural network over multiple agentscited by 277
  6. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  7. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  8. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  9. 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 159
  10. 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 73
  11. 2021Federated f-Differential Privacycited by 29
  12. 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
  13. 2022Homomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Casecited by 11
  14. 2023FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscationcited by 9
  15. 2020On the Difficulty of Membership Inference Attackscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 5.

10 papers.

  1. 2024FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysiscited by 6
  2. 2025Quantifying the Privacy Implications of High-Fidelity Synthetic Network Trafficcited by 3
  3. 2026Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approachcited by 3
  4. 2025FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classificationcited by 2
  5. 2025FLARE: A Wireless Side-Channel Fingerprinting Attack on Federated Learningcited by 1
  6. 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuningcited by 1
  7. 2026Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimizationcited by 1
  8. 2026Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMscited by 1
  9. 2025Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integritycited by 0
  10. 2026FLINT: Fingerprinting Federated Learning Architectures from 5G PHY-Layer Side Channelscited by 0