Abstract: This study introduces the Federated Edge-DP framework as a cutting edge approach for guaranteeing GDPR-compliant deployment of TinyML systems via a federated learning (FL) architecture embedded with the provision of differential privacy (DP). The proposed approach, combining lightweight noise injection and selective model partitions.....
Keywords Federated Learning, Differential Privacy, TinyML, GDPR Compliance, Edge AI, Privacy-preserving Machine Learning, Microcontrollers, Legal-Tech Integration, Secure Edge Deployment, Real-time Privacy Protection.
[1]. Dash, B., Sharma, P., & Ali, A. (2022). Federated learning for privacy-preserving: A review of PII data analysis in Fintech. International Journal of Software Engineering & Applications (IJSEA), 13(4).
[2]. Dutta, L., & Bharali, S. (2021). TinyML meets IoT: A comprehensive survey. Internet of Things, 16, 100461.
[3]. El Ouadrhiri, A., & Abdelhadi, A. (2022). Differential privacy for deep and federated learning: A survey. IEEE Access, 10, 22359–22380.
[4]. Jiang, B., Li, J., Yue, G., & Song, H. (2021). Differential privacy for industrial internet of things: Opportunities, applications, and challenges. IEEE Internet of Things Journal, 8(13), 10430–10451.
[5]. Jin, X., Katsis, C., Sang, F., Sun, J., Kundu, A., & Kompella, R. (2022). Edge security: Challenges and issues. arXiv preprint arXiv:2206.07164...