Privacy-Preserving and Secure AI-based Stress Monitoring Federated Learning on Wearable Edge Devices Using Homomorphic Encryption

The paper presents a new framework, HE-FedStress, with which it is feasible to monitor stress and preserve privacy in an AI-based approach to stress detection through federated learning and homomorphic encryption on wearable edge devices. The proposed system handles the essential privacy issues that come with decentralized health surveillance because the proposed system allows joint model training without exposing uncoded biometric information. The Edge wearable devices are local physiological signal temporal attention models that inference latency can process five-second windows with a latency of just 47 ms, implemented on photoplethysmography, electrodermal activity and accelerator data. The updates of the model are coded using the Pailier cryptosystem and sent to the central server where they could be aggregated securely without decrypting each individual contribution. The WESAD and SWELL-KW datasets have been empirically assessed to verify that HE-FedStress can give F1-scores of 89.7% and 85.2% respectively and retain centralized model performance with 92 and 94 % of this performance under full cryptographic protection against model-inversion attacks (compared to 34.7 % centralization in the standard federated learning case). The structure uses gradient quantization, which cuts down the communication load to 63KB/ round, and uses adaptive batch size to support heterogeneous device capacity. The computational optimizations (depthwise separable convolutions, selective attention pruning, and eight-bit quantization) allow incessant 24 hour execution of commercial wearables with only a 19% power consumption impact over plaintext federated learning. The design of the modular architecture is to meet GDPR and HIPAA data-localization standards and provide the ability to extend it to other healthcare applications. Therefore, this contribution can provide a practical, scalable stress monitoring solution to secure and personalized performance with a robust guarantee on cryptography, and can also indicate that the requirements of resource-constrained edge environments can be satisfied with a robust guarantee alongside real-time performance.

Secure Biometric Data, Federated Learning, Homomorphic Encryption, Wearable Edge Devices, Stress Monitoring.

1. Custodio, V., Herrera, F. J., López, G., & Moreno, J. I. (2012). A Review on Architectures and Communications Technologies for Wearable Health-Monitoring Systems. Sensors, 12(10), 13907-13946. https://doi.org/10.3390/s121013907. [Google Scholar] [Crossref]

2. Boonnithi, S., & Phongsuphap, S. (2011). Comparison of heart rate variability measures for mental stress detection. In Computing in Cardiology 2011, CinC 2011 (pp. 85-88). Article 6164508 (Computing in Cardiology; Vol. 38). [Google Scholar] [Crossref]

3. Liu, Y., & Du, S. (2018). Psychological stress level detection based on electrodermal activity. Behavioural brain research, 341, 50–53. https://doi.org/10.1016/j.bbr.2017.12.021 [Google Scholar] [Crossref]

4. Rashid, N., Mortlock, T., & Faruque, M. A. A. (2023). Stress detection using context-aware sensor fusion from wearable devices. IEEE Internet of Things Journal, 10(16), 14114–14127. https://doi.org/10.1109/JIOT.2023.3265768 [Google Scholar] [Crossref]

5. Xu, J., Glicksberg, B. S., Su, C., Walker, P., Bian, J., & Wang, F. (2021). Federated learning for healthcare informatics. Journal of Healthcare Informatics Research, 5(1), 1–19. https://doi.org/10.1007/s41666-020-00082-4. [Google Scholar] [Crossref]

6. Sun, T., Li, D., & Wang, B. (2023). Decentralized federated averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4289–4301. https://doi.org/10.1109/TPAMI.2022.3196503. [Google Scholar] [Crossref]

7. Zhang, L., Xu, J., Vijayakumar, P., Sharma, P. K., & Ghosh, U. (2023). Homomorphic encryption-based privacy-preserving federated learning in IoT-enabled healthcare system. IEEE Transactions on Network Science and Engineering, 10(5), 2864–2880. [Google Scholar] [Crossref]

8. https://doi.org/10.1109/TNSE.2022.3185327. [Google Scholar] [Crossref]

9. Wood, A., Najarian, K., & Kahrobaei, D. (2021). Homomorphic encryption for machine learning in medicine and bioinformatics. ACM Computing Surveys, 53(4), Article 70, 1–35. https://doi.org/10.1145/3394658. [Google Scholar] [Crossref]

10. Jost, C., Lam, H., Maximov, A., & Smeets, B. (2015). Encryption performance improvements of the Paillier cryptosystem. Cryptology ePrint Archive, Paper 2015/864. https://eprint.iacr.org/2015/864 [Google Scholar] [Crossref]

11. Liu, K., Xue, W., & Hou, D. (2025). Federated learning for nurse stress prediction using wearable sensors: Integrating biomechanical data. Molecular & Cellular Biomechanics, 22(5), 1699. https://doi.org/10.62617/mcb1699. [Google Scholar] [Crossref]

12. Kocabas, O., Soyata, T., Couderc, J.-P., Aktas, M., Xia, J., & Huang, M. (2013). Assessment of cloudbased health monitoring using homomorphic encryption. In Proceedings of the IEEE 31st International Conference on Computer Design (ICCD) (pp. 443–446). IEEE. https://doi.org/10.1109/ICCD.2013.6657078. [Google Scholar] [Crossref]

13. Alajlan, N. N., & Ibrahim, D. M. (2022). TinyML: Enabling of Inference Deep Learning Models on UltraLow-Power IoT Edge Devices for AI Applications. Micromachines, 13(6), 851. https://doi.org/10.3390/mi13060851. [Google Scholar] [Crossref]

14. Wu, H., Judd, P., Zhang, X., Isaev, M., & Micikevicius, P. (2020). Integer quantization for deep learning inference: Principles and empirical evaluation. arXiv. https://arxiv.org/abs/2004.09602 [Google Scholar] [Crossref]

15. Yu, S., Cui, L. (2023). Secure Multi-party Computation in Federated Learning. In: Security and Privacy in Federated Learning. Digital Privacy and Security. Springer, Singapore. https://doi.org/10.1007/978-981-19-8692-5_6. [Google Scholar] [Crossref]

16. Wei, K., Li, X., Chen, W., Li, J., & Li, Q. (2020). Federated learning with differential privacy: Algorithms and performance analysis. IEEE Transactions on Information Forensics and Security, 15, 3454–3469. https://doi.org/10.1109/TIFS.2020.2988575. [Google Scholar] [Crossref]

17. Tong, X., Li, Y., Zhang, H., & Chen, Z. (2024). Edge AI-enabled chicken health detection based on enhanced FCOS-Lite and knowledge distillation. Computers and Electronics in Agriculture, 226, 109432. https://doi.org/10.1016/j.compag.2024.109432. [Google Scholar] [Crossref]

18. Alammar, S., Aldawsari, H., AlSahly, A., AlGhamdi, K. A., & Khan, M. A. (2025). Federated explainable AI for privacy-preserving cardiovascular disease detection using wearable devices. IEEE Transactions on Consumer Electronics. https://doi.org/10.1109/TCE.2025.3647850. [Google Scholar] [Crossref]

19. Albshaier, L., Almarri, S., & Albuali, A. (2025). Federated Learning for Cloud and Edge Security: A Systematic Review of Challenges and AI Opportunities. Electronics, 14(5), 1019. https://doi.org/10.3390/electronics14051019. [Google Scholar] [Crossref]

20. Xi, L., Li, C., Anari, M. S., Chen, Y., & Zhang, H. (2025). Integrating wearable health devices with AI and edge computing for personalized rehabilitation. Journal of Cloud Computing, 14, 64. https://doi.org/10.1186/s13677-025-00795-0. [Google Scholar] [Crossref]

21. Khan, H. A., Nguyen, T. N., Shafiq, G., Mirza, J., & Javed, M. A. (2023). A secure wearable framework for stress detection in patients affected by communicable diseases. IEEE Sensors Journal, 23(2), 981–988. https://doi.org/10.1109/JSEN.2022.3204586. [Google Scholar] [Crossref]

22. D Dhinakaran, SE Raja, JJ Jasmine, et al. (2025) The Future of Well‐Being: AI‐Powered Health Management with Privacy at its Core. Powered By Ai. [Google Scholar] [Crossref]

23. Akram, M., Li, Y., Zhang, H., & Chen, Z. (2025). Toward TinyDPFL systems for real-time cardiac healthcare: Trends, challenges, and system-level perspectives on AI algorithms, hardware, and edge intelligence. Journal of Systems Architecture, 168, 103587. https://doi.org/10.1016/j.sysarc.2025.103587. [Google Scholar] [Crossref]

24. Chelliah, P. R., Rahmani, A. M., Colby, R., Nagasubramanian, G., & Ranganath, S. (Eds.). (2024). Model optimization methods for efficient and edge AI: Federated learning architectures, frameworks and applications (1st ed.). Wiley-IEEE Press. [Google Scholar] [Crossref]

25. Jain, A., Sharma, P., & Gupta, R. (2025). AI-driven wearable health devices with health-aware control and secure prognostics: Experimental and simulation-based validation. Array, 28, 100532. https://doi.org/10.1016/j.array.2025.100532. [Google Scholar] [Crossref]

26. Khan, A. R. (2025). Federated learning for next generation intelligent applications (PhD thesis, University of Glasgow). University of Glasgow. https://doi.org/10.5525/gla.thesis.85028 [Google Scholar] [Crossref]

27. Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018). Federated learning with non-IID data. arXiv. https://arxiv.org/abs/1806.00582. [Google Scholar] [Crossref]

28. Mao, Y., Zhao, Z., Yan, G., Liu, Y., Lan, T., Song, L., & Ding, W. (2022). Communication-efficient federated learning with adaptive quantization. ACM Transactions on Intelligent Systems and Technology, 13(4), Article 67, 1–26. https://doi.org/10.1145/3510587. [Google Scholar] [Crossref]

29. Li, J., Rakin, A. S., Chen, X., He, Z., Fan, D., & Chakrabarti, C. (2022). ResSFL: A resistance transfer framework for defending model inversion attack in split federated learning. In Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10184–10192). IEEE. https://doi.org/10.1109/CVPR52688.2022.00995. [Google Scholar] [Crossref]

30. Liu, B., Ding, M., Shaham, S., Rahayu, W., Farokhi, F., & Lin, Z. (2021). When machine learning meets privacy: A survey and outlook. ACM Computing Surveys, 54(2), Article 31, 1–36. https://doi.org/10.1145/3436755. [Google Scholar] [Crossref]

31. Dbouk, H., & Shanbhag, N. R. (2021). Generalized depthwise-separable convolutions for adversarially robust and efficient neural networks. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS 2021) (Article 920, pp. 12027–12039). Curran Associates Inc. [Google Scholar] [Crossref]

32. Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H. (2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2704–2713). IEEE. https://doi.org/10.1109/CVPR.2018.00286. [Google Scholar] [Crossref]

33. Mao, Y., Zhao, Z., Yan, G., Liu, Y., Lan, T., Song, L., & Ding, W. (2022). Communication-efficient federated learning with adaptive quantization. ACM Transactions on Intelligent Systems and Technology, 13(4), Article 51. https://doi.org/10.1145/3510587. [Google Scholar] [Crossref]

34. Reddi, S., Charles, Z., Zaheer, M., Garrett, Z., Rush, K., Konečný, J., Kumar, S., & McMahan, H. B. (2021). Adaptive federated optimization. arXiv. https://arxiv.org/abs/2003.00295. [Google Scholar] [Crossref]

35. Marcolla, C., Sucasas, V., Manzano, M., Bassoli, R., Fitzek, F. H. P., & Aaraj, N. (2022). Survey on fully homomorphic encryption, theory, and applications. Proceedings of the IEEE, 110(10), 1572–1609. https://doi.org/10.1109/JPROC.2022.3205665. [Google Scholar] [Crossref]

36. 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 (pp. 400–408). ACM. https://doi.org/10.1145/3242969.3242985. [Google Scholar] [Crossref]

37. Koldijk, S., Sappelli, M., Verberne, S., Neerincx, M. A., & Kraaij, W. (2014). The SWELL knowledge work dataset for stress and user modeling research. In Proceedings of the 2014 ACM Conference on User Modeling, Adaptation and Personalization (pp. 182–183). ACM. https://doi.org/10.1145/2663204.2663257. [Google Scholar] [Crossref]

38. Fawaz, S. M., Belal, N., ElRefaey, A., & Fakhr, M. W. (2021). A comparative study of homomorphic encryption schemes using Microsoft SEAL. Journal of Physics: Conference Series, 2128, 012021. https://doi.org/10.1088/1742-6596/2128/1/012021. [Google Scholar] [Crossref]

39. Shi, D., Li, L., Chen, R., Prakash, P., Pan, M., & Fang, Y. (2022). Toward energy-efficient federated learning over 5G+ mobile devices. IEEE Wireless Communications, 29(5), 44–51. https://doi.org/10.1109/MWC.003.2100028. [Google Scholar] [Crossref]

40. A., Imteaj, A., Thakker, U., Wang, S., Li, J., & Amini, M. H. (2022). A survey on federated learning for resource-constrained IoT devices. IEEE Internet of Things Journal, 9(1), 1–24. https://doi.org/10.1109/JIOT.2021.3095077. [Google Scholar] [Crossref]

41. Li, J., Rakin, A. S., Chen, X., Yang, L., He, Z., Fan, D., & Chakrabarti, C. (2023). Model extraction attacks on split federated learning. arXiv. https://arxiv.org/abs/2303.08581 [Google Scholar] [Crossref]

42. Abbas, Z., Ahmad, S. F., Syed, M. H., Anjum, A., & Rehman, S. (2024). Exploring deep federated learning for the Internet of Things: A GDPR-compliant architecture. IEEE Access, 12, 10548–10574. https://doi.org/10.1109/ACCESS.2023.3344029. [Google Scholar] [Crossref]

43. Baghersalimi, S., Teijeiro, T., Aminifar, A., & Atienza, D. (2024). Decentralized federated learning for epileptic seizures detection in low-power wearable systems. IEEE Transactions on Mobile Computing, 23(5), 6392–6407. https://doi.org/10.1109/TMC.2023.3320862. [Google Scholar] [Crossref]

44. Cremonesi, P. (2023). The need for multimodal health data modeling: A practical approach for a federated-learning healthcare platform. Journal of Biomedical Informatics, 141, 104338. https://doi.org/10.1016/j.jbi.2023.104338. [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition