CoChat

Advances and Open Problems in Federated Learning

Open access
Kairouz, Peter, McMahan, H. Brendan · 2021 · Foundations and Trends in Machine Learning

The DOI matches its Crossref record; 509 of the 514 references it cites were found in a registry or an index; 188 of the 503 sources its claims cite were checked for support.

Abstract

Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this monograph discusses recent advances and presents an extensive collection of open problems and challenges.

Overview

CoChat Summary

TL;DR

This paper is a broad survey of federated learning, and the provided text focuses on privacy, security, robustness, and fairness challenges rather than reporting a single empirical study. It argues that FL changes the attack surface and makes many standard defenses harder to deploy because of decentralization, limited client visibility, and communication constraints.

Key findings

  • Federated learning increases exposure to white-box evasion attacks because the model broadcast step means the model may be accessible to any malicious client; the text says this “increases the need for defenses against white-box evasion attacks.”
  • For model update poisoning, the paper notes that targeted attacks can be strong even with few adversaries: it reports that 10% of participating devices compromised can be enough to introduce a backdoor, even with anomaly detectors at the server.
  • Differential privacy is presented as a defense with two explicit strengths: it gives strong, worst-case protections and is closed under composition; but the paper also notes that in FL it can reduce accuracy and its hyperparameters are still hard to choose.
  • Under secure aggregation, the server sees only aggregates, which helps privacy, but the paper says the method has limitations: it assumes a semi-honest server in key setup, can still leak through per-round aggregates, is not efficient for sparse vectors, and does not enforce well-formed client inputs.

Methods

  • Not a single experimental study; this is a survey / open-problems paper organizing the FL literature across settings, efficiency, privacy, attacks, and fairness.
  • The text synthesizes prior work and uses qualitative analysis of threat models, privacy mechanisms (e.g., DP, secure aggregation, MPC, TEEs), and optimization results; it also reproduces convergence-rate tables for IID and non-IID federated optimization methods.
  • It discusses the FL setting using a cross-device / cross-silo / decentralized taxonomy and references typical FL workflows, datasets, and software frameworks rather than introducing new data collection.

Limitations

  • The paper explicitly states that many open questions remain: e.g., how to defend against inference-time attacks in FL, how to reconcile privacy with robust aggregation, and how to make secure aggregation compatible with non-linear defenses.
  • It says that formal analysis is often missing or incomplete for several areas, including split learning privacy guarantees, which are described as “still an open problem,” and the compatibility of some defenses with secure aggregation.
  • Evident from the text: because this is a survey, it does not present new experiments or a unified benchmark; conclusions are drawn from existing work and summarized tables, not from a new empirical evaluation.

Model-written summary of a shortened version of the paper’s full text (it is longer than we read). Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1561/2200000083

Cites

509 of 514 references verified1 citation errors · 4 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 The lifecycle of an FL-trained model and the various actors in a federated learning system. This figure is revisited in Section 4 from a threat models perspective.
Figure 1 The lifecycle of an FL-trained model and the various actors in a federated learning system. This figure is revisited in Section 4 from a threat models perspective.From the PDF
Figure 2 Split learning configurations showing raw data is not transferred in the vanilla setting and that raw data as well as labels are not transferred between the client and server entities in the U-shaped split learning setting.
Figure 2 Split learning configurations showing raw data is not transferred in the vanilla setting and that raw data as well as labels are not transferred between the client and server entities in the U-shaped split learning setting.From the PDF
Figure 1 The lifecycle of an FL-trained model and the various actors in a federated learning system. (repeated from Page 7)
Figure 1 The lifecycle of an FL-trained model and the various actors in a federated learning system. (repeated from Page 7)From the PDF
Figure 3 The Encode-Shuffle-Analyze (ESA) framework, illustrated here for 4 players.
Figure 3 The Encode-Shuffle-Analyze (ESA) framework, illustrated here for 4 players.From the PDF

Verification

Claims the paper makes

33 Valid · 129 Not valid · 141 Not checked · 285 Own results and interpretations

190 more claims · 51 with their cited sources checked

Create a free account to see all 588 claims and to verify the 13 references still open.

See all claims — free account
  • Probably not a substantial claim. 309
  • It may state two separate claims as one. 161

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

4 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Citations

Cites

Show all 514 references

Research works printed but not linked: 37

  1. McMahan, 2017, Federated learning: Collaborative machine learning without centralized training data
  2. Differential Privacy Team, 2017, Learning with privacy at scale, Apple Machine Learning Journal, 1
  3. Pichai, 2019, Google’s Sundar Pichai: Privacy should not be a luxury good
  4. Apple , Private federated learning (NeurIPS 2019 Expo Talk Abstract), https://nips.cc/ExpoConferences/2019/schedule?talk_id=40, 2019.
  5. Abadi, 2015, Tensor Flow: Large-scale machine learning on heterogeneous systems
  6. Tang, D2: Decentralized training over decentralized data
  7. Koloskova, Decentralized deep learning with arbitrary communication compression
  8. Jaderberg, Decoupled neural interfaces using synthetic gradients, 1627
  9. Wang, Adaptive communication strategies for best error-runtime trade-offs in communication-efficient distributed SGD
  10. He, Milenas: Efficient neural architecture search via mixed-level reformulation
  11. Han, Geometric lower bounds for distributed parameter estimation under communication constraints, 1
  12. Bell, Secure single-server aggregation with (poly)logarithmic overhead, 1253
  13. Andrew, How to generate and exchange secrets (extended abstract), 162
  14. Nikolaenko, Privacy-preserving ridge regression on hundreds of millions of records, 334
  15. Barak, 2019, Secure evaluation of quantized neural networks, IACR Cryptology ePrint Archive, 2019, 131
  16. 2020, Lattigo 2.0.0
  17. 2020, Microsoft SEAL (release 3.6)
  18. 2020, SHELL
  19. Intel, 2012, Architecture instruction set extensions programming reference
  20. Shi, Privacy-preserving aggregation of time-series data
  21. Lie, Glimmers: Resolving the privacy/trust quagmire, 94
  22. Sabater, 2020, Distributed differentially private averaging with improved utility and robustness to malicious parties
  23. Amin, Bounding user contributions: A bias-variance trade-off in differential privacy, 263
  24. Feldman, Privacy amplification by iteration, 521
  25. Balle, Advances in Neural Information Processing Systems, 4623
  26. Cummings, Differentially private change-point detection, 10825
  27. Cummings, Differential privacy for growing databases, 8864
  28. Tramèr, Stealing machine learning models via prediction APIs, 601
  29. Bassily, 2020, Practical locally private heavy hitters, J. Mach. Learn. Res., 21, 1
  30. Cummings, 2019, Bringing differential privacy into the experimental economics lab: Theory and an application to a public-good game
  31. Goodfellow, Explaining and harnessing adversarial examples
  32. Wang, 2020, Attack of the tails: Yes, you really can backdoor federated learning
  33. Barocas, 2019, Fairness and Machine Learning
  34. Richardson, 2019, Dirty data, bad predictions: How civil rights violations impact police data, predictive policing systems, and justice
  35. Sambasivan, ‘privacy is not for me, it’s for those rich women’: Performative privacy practices on mobile phones by women in South Asia, 127
  36. Madras, Learning adversarially fair and transferable representations
  37. Ramage, 2020, Federated analytics: Collaborative data science without data collection

Cited by

See all 7,772

Metadata

Authors
Kairouz, P., & McMahan, H. B.
Affiliations
  • Google Research, USA
  • Google (United States) (US)
Venue
Foundations and Trends in Machine Learning
Publisher
Emerald
Published
2021-06-23
Volume
14
Issue
1-2
Pages
1-210
ISSN
  • 1935-8237 (ISSN-L)
  • 1935-8245
OpenAlex
W2995022099
Cited by
7,772
References
451
Citations by year
2026: 1786 · 2025: 1736 · 2024: 1359 · 2023: 1149 · 2022: 781 · 2021: 665
FWCI
282.57
Type
journal article
Language
en
Open access
Locations
  • Foundations and Trends® in Machine Learning (publishedVersion)
  • Warwick Research Archive Portal (University of Warwick) (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • HAL (submittedVersion, other-oa)
  • HAL (submittedVersion, cc-by)
  • Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
  • LillOA (Université de Lille (University Of Lille)) (submittedVersion, other-oa)
  • Oskar-Bordeaux (Universite de Bordeaux) (submittedVersion)
  • Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
  • arXiv (Cornell University)
Funders
Agence Nationale de la Recherche (ANR-16-CE23-0016, ANR-20-CE23-0015)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
federated learning, decentralized data, privacy-preserving machine learning, data minimization, open problems, mobile devices, data collection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-02, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-02 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Advances and Open Problems in Federated Learning. https://app.cochat.ai/papers/10.1561/2200000083
The paper
Kairouz, P., & McMahan, H. B. (2021). Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning. https://doi.org/10.1561/2200000083

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.