Fedstress: A Privacy-Preserving Federated Learning Framework for Efficient and Accurate Stress Detection Using Wearable Sensors
Article Sidebar
Main Article Content
The proposed privacy-sensitive federated learning method is FedStress, which is aimed at identifying wearable stressors with high accuracy and efficiency. The growing use of wearables in health monitoring poses serious issues regarding data privacy and computational limitations especially in a situation where sensitive physiological data is to be used. The approaches in existence have inherent trade-offs: federated learning opens model parameters to gradient inversion attacks and differential privacy errors the accuracy by injecting noise and homomorphic encryption is prohibitive due to resource-constrained devices.
To solve these issues, FedStress combines federated learning with an optimized homomorphic encryption and allows collaborative model training without having access to raw user data. Every device trains locally a lightweight stress detector using a variant of MobileNetV3 using depthwise separable convolutions and a hybrid attention mechanism in order to trade off accuracy and efficiency. The encrypted transmission of model updates is done through partially homomorphic encryption, sensor-aware ciphertext packing which minimises overhead on encrypted model updates, and allows secure aggregation in the encrypted space.
An additional defense mechanism is on-device differential privacy with adaptive noise scaling, which prevents inference attacks and hierarchical key management which implements strict access control. Experimental confirmation of the WESAD dataset shows that FedStress can have 87.6% accuracy in detecting stress as centralized methods (89.1) with a much lower level of privacy risk, a gradient inversion attack success rate of 11% and a score of 0.09 on information leakage (0.45 with standard federated learning).
This framework is practical, with 23ms inference time and 0.45J of energy used to make a classification on commercial smartwatch systems due to efficient parameter synchronization and model compression. We also provide a viable solution to the current trend of privacy-conscious health monitoring systems, which offers a reasonable compromise between algorithmic performance and practical functionality of wearable applications. The modular structure also enables it to increase the physiological sensing tasks, which makes it a flexible instrument in studying edge-based federated learning.
Downloads
References
Pantelopoulos, A., & Bourbakis, N. G. (2010). A survey on wearable sensor-based systems for health monitoring and prognosis. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 40(1), 1–12. https://doi.org/10.1109/TSMCC.2009.2032660.
Dias, D., & Paulo Silva Cunha, J. (2018). Wearable Health Devices—Vital Sign Monitoring, Systems and Technologies. Sensors, 18(8), 2414. https://doi.org/10.3390/s18082414.
Can, Y. S., & Ersoy, C. (2021). Privacy-preserving federated deep learning for wearable IoT-based biomedical monitoring. ACM Transactions on Internet Technology, 21(1) https://doi.org/10.1145/3428152.
Li, L., Fan, Y., Tse, M., & Lin, K.-Y. (2020). A review of applications in federated learning. Computers & Industrial Engineering, 149, 106854. https://doi.org/10.1016/j.cie.2020.106854.
Miriyala, S. M. R., & Miriyala, S. (2020). Security and privacy preserving deep learning (arXiv preprint). arXiv. https://doi.org/10.48550/arXiv.2006.12698.
Chen, F., Li, S., Han, J., & et al. (2024). Review of lightweight deep convolutional neural networks. Archives of Computational Methods in Engineering, 31, 1915–1937. https://doi.org/10.1007/s11831-02310032-z.
Wang, Z., Yang, Z., Azimi, I., & Rahmani, A. M. (2024). Differential private federated transfer learning for mental health monitoring in everyday settings: A case study on stress detection. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 1–5). IEEE.
https://doi.org/10.1109/EMBC53108.2024.10782516.
Acar, A., Aksu, H., Uluagac, A. S., & Conti, M. (2019). A survey on homomorphic encryption schemes:
Theory and implementation. ACM Computing Surveys, 51(4), Article 79. https://doi.org/10.1145/3214303 9. Koç, Ç. K., Özdemir, F., & Ödemiş Özger, Z. (2021). Partially homomorphic encryption. Springer Cham. https://doi.org/10.1007/978-3-030-87629-6.
Jaiswal, D., Mukhopadhyay, S., & Sharma, V. (2024). TinyStressNet: On-device stress assessment with wearable sensors on edge devices. In 2024 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) (pp. 166–171). IEEE. https://doi.org/10.1109/PerComWorkshops59983.2024.10502631.
Kaissis, G., Ziller, A., Passerat-Palmbach, J., Ryffel, T., Usynin, D., Trask, A., Lima, I., Mancuso, J., Jungmann, F., Steinborn, M. M., Saleh, A., Makowski, M., Rueckert, D., & Braren, R. (2021). End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nature Machine Intelligence, 3(6), 473-484. https://doi.org/10.1038/s42256-021-00337-8.
Alharbey, R. A., & Jamil, F. (2025). Federated Learning Framework for Real-Time Activity and Context Monitoring Using Edge Devices. Sensors, 25(4), 1266. https://doi.org/10.3390/s25041266.
Gahlan, N., & Sethia, D. (2024). Federated learning inspired privacy sensitive emotion recognition based on multi-modal physiological sensors. Cluster Computing, 27, 3179–3201. https://doi.org/10.1007/s10586-023-04133-4.
Bussolan, A., Avram, O., Pignata, A., Urgese, G., Baraldo, S., & Valente, A. (2025). Personalized mental state evaluation in human-robot interaction using federated learning (arXiv preprint). arXiv. https://doi.org/10.48550/arXiv.2506.20212.
Schmidt, P., Reiss, A., Duerichen, R., Marberger, C., & Van Laerhoven, K. (2018). Introducing WESAD, a multimodal dataset for wearable stress and affect detection. In Proceedings of the 20th ACM International Conference on Multimodal Interaction (ICMI ’18). ACM. https://doi.org/10.1145/3242969.3242985.
Barnawi, A., Chhikara, P., Tekchandani, R., Kumar, N., & Alzahrani, B. (2024). A differentially privacy assisted federated learning scheme to preserve data privacy for IoMT applications. IEEE Transactions on Network and Service Management, 21(4). https://doi.org/10.1109/TNSM.2024.3393969.
Li, B., & Micciancio, D. (2021). On the security of homomorphic encryption on approximate numbers. In Advances in Cryptology – EUROCRYPT 2021 (Lecture Notes in Computer Science, Vol. 12696, pp. 489– 518). Springer. https://doi.org/10.1007/978-3-030-77870-5_23.
Erkin, Z., Veugen, T., Toft, T., & Lagendijk, R. L. (2012). Generating private recommendations efficiently using homomorphic encryption and data packing. IEEE Transactions on Information Forensics and Security, 7(3), 1053–1066. https://doi.org/10.1109/TIFS.2012.2190726.
Pramudhita, D. A., Azzahra, F., Arfat, I. K., Magdalena, R., & Saidah, S. (2023). Strawberry Plant
Diseases Classification Using CNN Based on MobileNetV3-Large and EfficientNet-B0 Architecture. Jurnal Ilmiah Teknik Elektro Komputer Dan Informatika, 9(3), 522–534. https://doi.org/10.26555/jiteki.v9i3.26341.
Gou, J., Yu, B., Maybank, S. J., & et al. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129, 1789–1819. https://doi.org/10.1007/s11263-021-01453-z.
Wijsman, J., Grundlehner, B., Liu, H., Hermens, H., & Penders, J. (2011). Towards mental stress detection using wearable physiological sensors. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2011, 1798–1801. https://doi.org/10.1109/IEMBS.2011.6090512.
Zhang, Y., Zheng, X. T., Zhang, X., Pan, J., & Thean, A. V. (2024). Hybrid Integration of Wearable Devices for Physiological Monitoring. Chemical reviews, 124(18), 10386–10434. https://doi.org/10.1021/acs.chemrev.3c00471.
Becker, M., Matt, C., Widjaja, T., & Hess, T. (2017). Understanding privacy risk perceptions of consumer health wearables – An empirical taxonomy. In Proceedings of the 38th International Conference on Information Systems (ICIS 2017). Seoul, South Korea.
Venkatesaramani, R., Malin, B. A., & Vorobeychik, Y. (2021). Re-identification of individuals in genomic datasets using public face images. Science Advances, 7(47), eabg3296. https://doi.org/10.1126/sciadv.abg3296.
Tzanou, M. (Ed.). (2020). Health Data Privacy under the GDPR: Big Data Challenges and Regulatory Responses (1st ed.). Routledge. https://doi.org/10.4324/9780429022241.
Gahlan, N., & Sethia, D. (2025). Federated learning in emotion recognition systems based on physiological signals for privacy preservation: A review. Multimedia Tools and Applications, 84, 12417– 12485. https://doi.org/10.1007/s11042-024-19467-3.
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60. https://doi.org/10.1109/MSP.2020.2975749.
Lu, Z., Pan, H., Dai, Y., Si, X., & Zhang, Y. (2024). Federated learning with non-IID data: A survey. IEEE Internet of Things Journal, 11(11), 19188–19209. https://doi.org/10.1109/JIOT.2024.3376548.
McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. y. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Vol. 54, pp. 1273–1282). Proceedings of Machine Learning Research. https://proceedings.mlr.press/v54/mcmahan17a.html.
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated optimization in heterogeneous networks. In I. Dhillon, D. Papailiopoulos, & V. Sze (Eds.), Proceedings of Machine Learning and Systems (Vol. 2, pp. 429–450).
Gentry, C. (2009). Fully homomorphic encryption using ideal lattices. In Proceedings of the 41st Annual ACM Symposium on Theory of Computing (STOC ’09). ACM. https://doi.org/10.1145/1536414.1536440.
Cheon, J.H., Kim, A., Kim, M., Song, Y. (2017). Homomorphic Encryption for Arithmetic of Approximate Numbers. In: Takagi, T., Peyrin, T. (eds) Advances in Cryptology – ASIACRYPT 2017. ASIACRYPT 2017. Lecture Notes in Computer Science(), vol 10624. Springer, Cham. https://doi.org/10.1007/978-3319-70694-8_15.
Wang, J., Liu, Q., Liang, H., Joshi, G., & Poor, H. V. (2020). Tackling the objective inconsistency problem in heterogeneous federated optimization. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in Neural Information Processing Systems (Vol. 33, pp. 7611–7623). Curran Associates, Inc.
Fallah, A., Mokhtari, A., & Ozdaglar, A. (2020). Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in Neural Information Processing Systems (Vol. 33, pp. 3557–3568). Curran Associates, Inc.
Yurochkin, M., Agarwal, A., Ghosh, S., Greenewald, K., Nguyen, H. V., & Tran, L. (2020). Bayesian nonparametric federated learning of neural networks (arXiv preprint). arXiv. https://doi.org/10.48550/arXiv.2010.08762.
Geiping, J., Bauermeister, H., Dröge, H., & Moeller, M. (2020). Inverting gradients – How easy is it to break privacy in federated learning? In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in Neural Information Processing Systems (Vol. 33, pp. 16937–16947). Curran Associates, Inc.
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in our journal are licensed under CC-BY 4.0, which permits authors to retain copyright of their work. This license allows for unrestricted use, sharing, and reproduction of the articles, provided that proper credit is given to the original authors and the source.