mlsanityData to 7 Oct 2026

Source Inference Attacks in Federated Learning

arXiv 2109.05659 ↗First posted 13 Sep 2021cs.CR cs.DC cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership inference attacks (MIAs) that can distinguish the training members of the given model from the non-members. However, existing MIAs ignore the source of a training member, i.e., the information of which client owns the training member, while it is essential to explore source privacy in FL beyond membership privacy of examples from all clients. The leakage of source information can lead to severe privacy issues. For example, identification of the hospital contributing to the training of an FL model for COVID-19 pandemic can render the owner of a data record from this hospital more prone to discrimination if the hospital is in a high risk region. In this paper, we propose a new inference attack called source inference attack (SIA), which can derive an optimal estimation of the source of a training member. Specifically, we innovatively adopt the Bayesian perspective to demonstrate that an honest-but-curious server can launch an SIA to steal non-trivial source information of the training members without violating the FL protocol. The server leverages the prediction loss of local models on the training members to achieve the attack effectively and non-intrusively. We conduct extensive experiments on one synthetic and five real datasets to evaluate the key factors in an SIA, and the results show the efficacy of the proposed source inference attack.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

25 of 40 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  6. 2018Federated Learning with Non-IID Datacited by 1,099
  7. 2019Deep Leakage from Gradientscited by 1,004
  8. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  9. 2018How To Backdoor Federated Learningcited by 745
  10. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  11. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  12. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
13 more
  1. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  2. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  3. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  4. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
  5. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  6. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  7. 2017Machine Learning Models that Remember Too Muchcited by 165
  8. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  9. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 63
  10. 2020Federated Model Distillation with Noise-Free Differential Privacycited by 40
  11. 2018Towards Demystifying Membership Inference Attackscited by 39
  12. 2020Secure Deep Graph Generation with Link Differential Privacycited by 24
  13. 2021Membership Inference Attacks on Knowledge Graphscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 5; 2024: 5; 2025: 7; 2026: 7.

31 papers.

Sort:

By area:

  1. 2022M^4I: Multi-modal Models Membership Inferencecited by 30
  2. 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 19
  3. 2021Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settingscited by 12
  4. 2023FedDWA: Personalized Federated Learning with Dynamic Weight Adjustmentcited by 9
  5. 2022Flow: Per-Instance Personalized Federated Learning Through Dynamic Routingcited by 6
  6. 2023Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMIcited by 6
  7. 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learningcited by 4
  8. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
  9. 2023On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directionscited by 3
  10. 2025Equitable Federated Learning with NCAcited by 3
  11. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learningcited by 2
  12. 2022Local Model Reconstruction Attacks in Federated Learning and their Usescited by 2
19 more
  1. 2024No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learningcited by 2
  2. 2024Inference Attacks: A Taxonomy, Survey, and Promising Directionscited by 2
  3. 2025FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Riskcited by 2
  4. 2024Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defensecited by 1
  5. 2024SoK: Towards Security and Safety of Edge AIcited by 1
  6. 2026SoK: Challenges in Tabular Membership Inference Attackscited by 1
  7. 2026CQSA: Byzantine-robust Clustered Quantum Secure Aggregation in Federated Learningcited by 1
  8. 2022Efficient and Privacy Preserving Group Signature for Federated Learningcited by 0
  9. 2024Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Themcited by 0
  10. 2025Mitigating Membership Inference Vulnerability in Personalized Federated Learningcited by 0
  11. 2025Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learningcited by 0
  12. 2025Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approachcited by 0
  13. 2025Multi-Hop Privacy Propagation for Differentially Private Federated Learning in Social Networkscited by 0
  14. 2025Accurate and Private Diagnosis of Rare Genetic Syndromes from Facial Images with Federated Deep Learningcited by 0
  15. 2026ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregationcited by 0
  16. 2026IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learningcited by 0
  17. 2026PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learningcited by 0
  18. 2026Protecting patient privacy in clinical foundation models: Technical and legal perspectivescited by 0
  19. 2026Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunitiescited by 0