MLGuard: Mitigating Poisoning Attacks in Privacy Preserving Distributed Collaborative Learning
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Distributed collaborative learning has enabled building machine learning models from distributed mobile users' data. It allows the server and users to collaboratively train a learning model where users only share model parameters with the server. To protect privacy, the server can use secure multiparty computation to learn the global model without revealing users' parameter updates in the clear. However this privacy preserving distributed learning opens the door to poisoning attacks, where malicious users poison their training data to maliciously influence the behavior of the global model. In this paper, we propose MLGuard, a privacy preserving distributed collaborative learning system with poisoning attack mitigation. MLGuard employs lightweight secret sharing scheme and a novel poisoning attack mitigation technique. We address several challenges such as preserving users' privacy, mitigating poisoning attacks, respecting resource constraints of mobile devices, and scaling to large number of users. Evaluation results demonstrate the effectiveness of MLGuard on building high accurate learning models with the existence of malicious users, while imposing minimal communication cost on mobile devices.
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
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956 · cited 3×
“al [9] proposed a collaborative learning solution which leverages secure multiparty computation to aggregate all parameter updates obtained from users’ devices without revealing users’ updates in the clear.”
BackgroundPrivacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 5×
“A typical implementation of collaborative learning is referred to as collaborative learning with synchronized gradient updates [6] which works as follows.”
BackgroundInfluentialExploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734
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 1×
“Recent studies show that mobile devices are attractive targets to adversaries [24], and thus poisoning attacks can be launched by compromised these devices [17] [25].”
BackgroundMultiparty Computation from Somewhat Homomorphic Encryption
Damgård, I., Pastro, V., Smart, N., & Zakarias, S. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-32009-5_38 · Cited by 1,331 · cited 1×
“In this subsection, we introduce the privacy preserving training which relies on additive secret sharing scheme [15] [16] to secretly share the parameter updates among the two servers.”
MethodPoisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331
Federated Learning for Mobile Keyboard Prediction
Hard, A., Rao, K., Mathews, R., Ramaswamy, S., Beaufays, F., Augenstein, S., Eichner, H., Kiddon, C., & Ramage, D. (2018) · arXiv · doi:10.48550/arxiv.1811.03604 · Cited by 1,148 · cited 1×
“Such models have been used in many intelligent applications, including image recognition [1], speech recognition [2] [3], and next-word prediction [4].”
MethodMitigating Sybils in Federated Learning Poisoning
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2018) · arXiv · doi:10.48550/arxiv.1808.04866 · Cited by 385 · cited 2×
“Several works studied mitigating poisoning attacks in collaborative learning [17] [13] [14].”
BackgroundA uror: defending against poisoning attacks in collaborative deep learning systems
Shen, S., Tople, S., & Saxena, P. (2016) · Proceedings of the 32nd Annual Conference on Computer Security Applications · doi:10.1145/2991079.2991125 · Cited by 228 · cited 3×
“Several works studied mitigating poisoning attacks in collaborative learning [17] [13] [14].”
Background
Cited by
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
DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
Rieger, P., Nguyen, T. D., Miettinen, M., & Sadeghi, A.-R. (2022) · Proceedings 2022 Network and Distributed System Security Symposium · doi:10.14722/ndss.2022.23156 · Cited by 202
Review on Federated Learning for digital transformation in healthcare through big data analytics
Babar, M., Qureshi, B., & Koubaa, A. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.05.046 · Cited by 55
Mitigating the Backdoor Attack by Federated Filters for Industrial IoT Applications
Hou, B., Gao, J., Guo, X., Baker, T., Zhang, Y., Wen, Y., & Liu, Z. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3112100 · Cited by 49
Threats and Defenses in the Federated Learning Life Cycle: A Comprehensive Survey and Challenges
Li, Y., Guo, Z., Yang, N., Chen, H., Yuan, D., & Ding, W. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3563537 · Cited by 38
“MLGuard [172] further enhances the robustness of secret sharing-based FL to poisoning attacks.”
Metadata
- Authors
- Khazbak, Y., Tan, T., & Cao, G.
- Venue
- 2020 29th International Conference on Computer Communications and Networks (ICCCN)
- Publisher
- IEEE
- Published
- 2020-08
- Pages
- 1-9
- ISSN
- 1095-2055 (ISSN-L)
- OpenAlex
- W3090750097
- Cited by
- 39
- References
- 11
- FWCI
- 2.32
- Type
- conference paper
- Language
- en
- Open access
- closed
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
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.