Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 177 of the 177 references it cites were found in a registry or an index.

A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy

Open access
Manzoor, Habib Ullah, Shabbir, Attia, Chen, Ao, Flynn, David, Zoha, Ahmed · 2024 · Future Internet

Abstract

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling decentralized model training across multiple devices while preserving data privacy. However, the decentralized nature of FL introduces significant security challenges, making it vulnerable to various attacks targeting models, data, and privacy. This survey provides a comprehensive overview of the defense strategies against these attacks, categorizing them into data and model defenses and privacy attacks. We explore pre-aggregation, in-aggregation, and post-aggregation defenses, highlighting their methodologies and effectiveness. Additionally, the survey delves into advanced techniques such as homomorphic encryption and differential privacy to safeguard sensitive information. The integration of blockchain technology for enhancing security in FL environments is also discussed, along with incentive mechanisms to promote active participation among clients. Through this detailed examination, the survey aims to inform and guide future research in developing robust defense frameworks for FL systems.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/fi16100374

Cites

177 of 177 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Paper distribution.
Figure 1 Paper distribution.CC-BY · From the PDF
Figure 2 Overview of FL.
Figure 2 Overview of FL.CC-BY · From the PDF
Image 3
CC-BY · From the PDF
Figure 4 Types of attacks in FL.
Figure 4 Types of attacks in FL.CC-BY · From the PDF
Figure 5 Types of defense strategies.
Figure 5 Types of defense strategies.CC-BY · From the PDF
Figure 6 Visual representation of detect and remove defense strategy.
Figure 6 Visual representation of detect and remove defense strategy.CC-BY · From the PDF
Figure 7 Visual representation of adversarial training.
Figure 7 Visual representation of adversarial training.CC-BY · From the PDF
Structured Pruning
Structured PruningCC-BY · From the PDF
Unstructured Pruning
Unstructured PruningCC-BY · From the PDF
Figure 9 Visual representation of byzantine robust aggregation techniques.
Figure 9 Visual representation of byzantine robust aggregation techniques.CC-BY · From the PDF
Figure 10 Visual representation of robust client selection.
Figure 10 Visual representation of robust client selection.CC-BY · From the PDF
Image 12
CC-BY · From the PDF
Figure 12 Visual representation of blockchain.
Figure 12 Visual representation of blockchain.CC-BY · From the PDF
Figure 13 Visual representation of Incentivized Federated Learning.
Figure 13 Visual representation of Incentivized Federated Learning.CC-BY · From the PDF
Figure 14 Visual representation of regularization.
Figure 14 Visual representation of regularization.CC-BY · From the PDF
Figure 15 Visual representation of homomorphic encryption.
Figure 15 Visual representation of homomorphic encryption.CC-BY · From the PDF
Figure 16 Visual representation of knowledge distillation.
Figure 16 Visual representation of knowledge distillation.CC-BY · From the PDF
Figure 17 Visual representation of Secure Multi-party Computation.
Figure 17 Visual representation of Secure Multi-party Computation.CC-BY · From the PDF
Figure 18 Visual representation of split learning.
Figure 18 Visual representation of split learning.CC-BY · From the PDF
Figure 19 Visual representation of perturbing gradients.
Figure 19 Visual representation of perturbing gradients.CC-BY · From the PDF
Figure 20 Visual representation of differential privacy.
Figure 20 Visual representation of differential privacy.CC-BY · From the PDF
Figure 21 Visual representation of Trusted Execution Environments (TEEs).
Figure 21 Visual representation of Trusted Execution Environments (TEEs).CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 158 references

Research works printed but not linked: 10

  1. Badi, 2024, IoT and Big Data Analytics: Revolutionizing Business and Society with Advanced Insights, Int. J. Appl. Math. Comput. Sci., 3, 42
  2. Shen, S., Tople, S., and Saxena, P. (2016, January 5–9). Auror: Defending against poisoning attacks in collaborative deep learning systems. Proceedings of the 32nd Annual Conference on Computer Security Applications, Los Angeles, CA, USA.
  3. Muñoz-González, L., Co, K.T., and Lupu, E.C. (2019). Byzantine-robust federated machine learning through adaptive model averaging. arXiv.
  4. Balakrishnan, R., Li, T., Zhou, T., Himayat, N., Smith, V., and Bilmes, J. (2022, January 25–29). Diverse client selection for federated learning via submodular maximization. Proceedings of the International Conference on Learning Representations, Virtual.
  5. Yan, G., Lyu, S., Hou, H., Zheng, Z., and Song, L. (2024). Towards Quantum-Safe Federated Learning via Homomorphic Encryption: Learning with Gradients. arXiv.
  6. Liu, Y., Zou, T., Kang, Y., Liu, W., He, Y., Yi, Z., and Yang, Q. (2021). Batch label inference and replacement attacks in black-boxed vertical federated learning. arXiv.
  7. Sengupta, A., Dixit, S., Akhtar, M.S., and Chakraborty, T. (2023, January 25–29). A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation. Proceedings of the The Twelfth International Conference on Learning Representations, Virtual Event.
  8. Lan, W., Cheung, Y.m., Xu, Q., Liu, B., Hu, Z., Li, M., and Chen, Z. (2024). Improve Knowledge Distillation via Label Revision and Data Selection. arXiv.
  9. Mugunthan, V., Polychroniadou, A., Byrd, D., and Balch, T.H. (2019, January 13). Smpai: Secure multi-party computation for federated learning. Proceedings of the NeurIPS 2019 Workshop on Robust AI in Financial Services, Vancouver, BC, Canada.
  10. Wang, S., Zhu, T., Liu, B., Ming, D., Guo, X., Ye, D., and Zhou, W. (2024). Unique Security and Privacy Threats of Large Language Model: A Comprehensive Survey. arXiv.

Cited by

See all 77

Metadata

Authors
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A.
Affiliations
  • University of Glasgow (GB)
  • Ghulam Ishaq Khan Institute of Engineering Sciences and Technology (PK)
Corresponding author
Zoha, Ahmed
Venue
Future Internet
Publisher
MDPI AG
Published
2024-10-15
Volume
16
Issue
10
Pages
374
ISSN
1999-5903 (ISSN-L)
OpenAlex
W4403429393
Cited by
58
References
158
Citations by year
2026: 31 · 2025: 22 · 2024: 5
FWCI
8.59
Type
journal article
Language
en
Open access
Locations
  • Future Internet (publishedVersion, cc-by)
  • ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (acceptedVersion, cc-by-sa)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
Engineering and Physical Sciences Research Council (EP/Y002288/1)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
Keywords
federated learning security, data poisoning, model poisoning, privacy attacks, homomorphic encryption, differential privacy, blockchain, incentive mechanisms, data privacy

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.

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: A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy. https://app.cochat.ai/papers/10.3390/fi16100374
The paper
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024). A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy. Future Internet. https://doi.org/10.3390/fi16100374

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.