Dynamic defense against byzantine poisoning attacks in federated learning
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Federated learning, as a distributed learning that conducts the training on the local devices without accessing to the training data, is vulnerable to Byzatine poisoning adversarial attacks. We argue that the federated learning model has to avoid those kind of adversarial attacks through filtering out the adversarial clients by means of the federated aggregation operator. We propose a dynamic federated aggregation operator that dynamically discards those adversarial clients and allows to prevent the corruption of the global learning model. We assess it as a defense against adversarial attacks deploying a deep learning classification model in a federated learning setting on the Fed-EMNIST Digits, Fashion MNIST and CIFAR-10 image datasets. The results show that the dynamic selection of the clients to aggregate enhances the performance of the global learning model and discards the adversarial and poor (with low quality models) clients.
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.
Integrity signals
Registry
Cites
Statistics
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.
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“1 The Fed-EMNIST (Federated Extended Modified NIST) dataset, which was presented in 2017 in [19] as an extension of the MNIST dataset [46].”
MethodFashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
Federated Optimization: Distributed Machine Learning for On-Device Intelligence
Konečný, J., McMahan, H. B., Ramage, D., & Richtárik, P. (2016) · arXiv · doi:10.48550/arxiv.1610.02527 · Cited by 1,563
How to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495 · cited 4×
“2 Depending on the purpose of the attack, we distinguish between untargeted or byzantine attacks [35], which seek to affect the model’s performance, and targeted or backdoor attacks [17], which aim at injecting a secondary or backdoor task into the global model by stealth.”
BackgroundInfluentialA survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T., Liu, K., Dolan-Gavitt, B., & Garg, S. (2019) · IEEE Access · doi:10.1109/access.2019.2909068 · Cited by 1,238 · cited 2×
“Accordingly, poisoning attacks, both data and (local) model poisoning [10, 11], grounded in the malicious manipulation of the training data or the local model updates, can corrupt the FL model, which cannot inspect the training to defend itself against this kind of adversarial attacks.”
Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D. (2011) · Proceedings of the 4th ACM workshop on Security and artificial intelligence · doi:10.1145/2046684.2046692 · Cited by 1,194 · cited 2×
“Machine learning is highly susceptible to adversarial attacks [25], and the vast majority of the defensive approaches are based on three approaches [8]: (1) game theory [26], (2) data sanitation [27] and (3) resilient and robust learning models, which assume that a fraction of the training data may be manipulated and…”
BackgroundByzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Yin, D., Chen, Y., Ramchandran, K., & Bartlett, P. (2018) · arXiv · doi:10.48550/arxiv.1803.01498 · Cited by 1,130
Data Poisoning Attacks Against Federated Learning Systems
Tolpegin, V., Truex, S., Gursoy, M. E., & Liu, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58951-6_24 · Cited by 927
Cited by
Survey: federated learning data security and privacy-preserving in edge-Internet of Things
Li, H., Ge, L., & Tian, L. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10774-7 · Cited by 112
“In terms of defending data security attacks, Nuria et al. (Rodríguez-Barroso et al. 2022b) deeply analyzed the model poisoning backdoor attack in FL, discussed the pattern key backdoor attack and distributed backdoor attack that may be triggered by adversarial participants with outlier behaviors in FL, and developed a…”
A robust analysis of adversarial attacks on federated learning environments
Nair, A. K., Raj, E. D., & Sahoo, J. (2023) · Computer Standards & Interfaces · doi:10.1016/j.csi.2023.103723 · Cited by 70
A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024) · Future Internet · doi:10.3390/fi16100374 · Cited by 58
Metadata
- Authors
- Rodríguez-Barroso, N., Martínez-Cámara, E., Luzón, M. V., & Herrera, F.
- Venue
- Future Generation Computer Systems
- Publisher
- Elsevier BV
- Published
- 2022-08
- Volume
- 133
- Pages
- 1-9
- ISSN
- 0167-739X (ISSN-L)
- OpenAlex
- W4220837705
- Cited by
- 54
- References
- 26
- FWCI
- 3.80
- Type
- journal article
- Language
- en
- Open access
- green
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: Dynamic defense against byzantine poisoning attacks in federated learning. https://app.cochat.ai/papers/10.1016/j.future.2022.03.003
- The paper
- Rodríguez-Barroso, N., Martínez-Cámara, E., Luzón, M. V., & Herrera, F. (2022). Dynamic defense against byzantine poisoning attacks in federated learning. Future Generation Computer Systems. https://doi.org/10.1016/j.future.2022.03.003
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.