Preserving User Privacy for Machine Learning: Local Differential Privacy or Federated Machine Learning?
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
The growing number of mobile and IoT devices has nourished many intelligent applications. In order to produce high-quality machine learning models, they constantly access and collect rich personal data such as photos, browsing history, and text messages. However, direct access to personal data has raised increasing public concerns about privacy risks and security breaches. To address these concerns, there are two emerging solutions to privacy-preserving machine learning, namely local differential privacy and federated machine learning. The former is a distributed data collection strategy where each client perturbs data locally before submitting to the server, whereas the latter is a distributed machine learning strategy to train models on mobile devices locally and merge their output (e.g., parameter updates of a model) through a control protocol. In this article, we conduct a comparative study on the efficiency and privacy of both solutions. Our results show that in a standard population and domain setting, both can achieve an optimal misclassification rate lower than 20% and federated machine learning generally performs better at the cost of higher client CPU usage. Nonetheless, local differential privacy can benefit more from a larger client population ($>$> 1k). As for privacy guarantee, local differential privacy also has flexible control over the data leakage.
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
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
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
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 2×
“…FML for a loose federation of multiple mobile clients with scalable design 5 and develops secure aggregation using encryption scheme such as MPC. 13 As for the system aspects, the architecture of federated learning discussed in this article is horizontal design, 19 which enables easy unification…”
MethodFederated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565 · cited 1×
“Particularly, horizontal federated systems in mobile edge computing have started to study differentially private version by injecting noises to either SGD process or the final updates.(20)”
BackgroundRobust De-anonymization of Large Sparse Datasets
Narayanan, A., & Shmatikov, V. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.33 · Cited by 2,372 · cited 1×
“, generalization) and encryption schemes are shown vulnerable to various attacks, such as deanonymizing Netflix challenge dataset with IMDb data.(3) More recently, two distributed data analytical tools are proposed to protect privacy, namely, local differential privacy (LDP)(4) and federated machine learning (FML).”
BackgroundRAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
Erlingsson, Ú., Pihur, V., & Korolova, A. (2014) · Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2660267.2660348 · Cited by 1,838
Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., & Backes, M. (2019) · Proceedings 2019 Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23119 · Cited by 852
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · arXiv · doi:10.48550/arxiv.1902.04885 · Cited by 600
Differentially-Private "Draw and Discard" Machine Learning
Pihur, V., Korolova, A., Liu, F., Sankuratripati, S., Yung, M., Huang, D., & Zeng, R. (2018) · arXiv · doi:10.48550/arxiv.1807.04369 · Cited by 25
Cited by
Yin, X., Zhu, Y., & Hu, J. (2022) · ACM Computing Surveys · doi:10.1145/3460427 · Cited by 638
A state-of-the-art survey on solving non-IID data in Federated Learning
Ma, X., Zhu, J., Lin, Z., Chen, S., & Qin, Y. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.05.003 · Cited by 399
Privacy-Preserving Federated Learning with Resource Adaptive Compression for Edge Devices
Hidayat, M. A., Nakamura, Y., & Arakawa, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3347552 · Cited by 29
“This process is repeated multiple times until the desired learning objectives are met, as outlined in [37].”
BackgroundDifferential Privacy in Cognitive Radio Networks: A Comprehensive Survey
Ul Hassan, M., Rehmani, M. H., Rehan, M., & Chen, J. (2022) · Cognitive Computation · doi:10.1007/s12559-021-09969-9 · Cited by 19
Metadata
- Authors
- Zheng, H., Hu, H., & Han, Z.
- Venue
- IEEE Intelligent Systems
- Published
- 2020-07-01
- Volume
- 35
- Issue
- 4
- Pages
- 5-14
- ISSN
- 1541-1672 (ISSN-L)
- 1941-1294
- OpenAlex
- W3044796230
- Cited by
- 96
- References
- 9
- FWCI
- 4.92
- 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
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.