Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity Recognition
Open accessAbstract
Wearable devices and smartphones that are used to monitor the activity and the state of the driver collect a lot of sensitive data such as audio, video, location and even health data. The analysis and processing of such data require observing the strict legal requirements for personal data security and privacy. The federated learning (FL) computation paradigm has been proposed as a privacy-preserving computational model that allows securing the privacy of the data owner. However, it still has no formal proof of privacy guarantees, and recent research showed that the attacks targeted both the model integrity and privacy of the data owners could be performed at all stages of the FL process. This paper focuses on the analysis of the privacy-preserving techniques adopted for FL and presents a comparative review and analysis of their implementations in the open-source FL frameworks. The authors evaluated their impact on the overall training process in terms of global model accuracy, training time and network traffic generated during the training process in order to assess their applicability to driver’s state and behaviour monitoring. As the usage scenario, the authors considered the case of the driver’s activity monitoring using the data from smartphone sensors. The experiments showed that the current implementation of the privacy-preserving techniques in open-source FL frameworks limits the practical application of FL to cross-silo settings.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
There is no formal proof of privacy guarantees for the federated learning process.
“Additionally, there is no formal proof of privacy guarantees [19] for the FL process as there is a possibility of security attack due to inherent vulnerabilities associated with a distributed system.”
From A Review of Privacy Enhancement Methods for Federated Learning in Healthcare Systems (2023) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 60 · Cited by 24
Research works printed but not linked: 9
- [27]Ding B. Kulkarni J. Yekhanin S. Collecting Telemetry Data Privately Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17) Long Beach, CA, USA 4–9 December 2017 Curran Associates Inc. Red Hook, NY, USA 2017 3574 3583
- [37]Xu D. Yuan S. Wu X. Achieving Differential Privacy in Vertically Partitioned Multiparty Learning arXiv 2019 1911.04587
- [45]Liu Y. Kang Y. Zhang X. Li L. Cheng Y. Chen T. Hong M. Yang Q. A Communication Efficient Vertical Federated Learning Framework arXiv 2019 1912.11187
- [49]Aloufi A. Hu P. Collaborative Homomorphic Computation on Data Encrypted under Multiple Keys arXiv 2019 1911.04101
- [58]So J. Ali R.E. Guler B. Jiao J. Avestimehr S. Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning arXiv 2021 2106.03328
- [60]Choi B. yong Sohn J. Han D.J. Moon J. Communication-Computation Efficient Secure Aggregation for Federated Learning arXiv 2020 2012.05433
- [62]Kadhe S. Rajaraman N. Koyluoglu O.O. Ramchandran K. FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning arXiv 2020 2009.11248
- [76]Zhang Y. Zhu H. Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning arXiv 2020 2007.06849
- [77]Naor M. Pinkas B. Efficient Oblivious Transfer Protocols Proceedings of the Twelfth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA’01) Washington, DC, USA 7–9 January 2001 Society for Industrial and Applied Mathematics Philadelphia, PA, USA 2001 448 457
- Authors
- Novikova, E., Fomichov, D., Kholod, I., & Filippov, E.
- Affiliations
- Saint Petersburg State Electrotechnical University (RU)
- Smartilizer Rus LLC, Saint Petersburg 197376, Russia
- Corresponding author
- Novikova, Evgenia
- Filippov, Evgeny
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2022-04-13
- Volume
- 22
- Issue
- 8
- Pages
- 2983
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC9029817
- OpenAlex
- W4224100171
- Cited by
- 24
- References
- 60
- Citations by year
- 2026: 3 · 2025: 2 · 2024: 4 · 2023: 5 · 2022: 10
- FWCI
- 1.73
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Physical Sciences › Computer Science › Artificial Intelligence › Cryptography and Data Security
- Keywords
- federated learning, privacy-preserving techniques, driver activity recognition, driver state monitoring, wearable devices, smartphone sensors, cross-silo federated learning, privacy attacks
- MeSH terms
- Learning, Technology, Computer Security, Privacy, Recognition, Psychology
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
