Enabling Real-Time AI at the Edge: Federated Learning Framework with Privacy Preservation

Prof. Abhishek Vishwakarma; Prof. Shivam  Tiwari; Prof. Ranu  Sahu; Prashu  Jain; Sakshi  Jain

doi:10.15680/IJIRCCE.2023.1106071

Prof. Abhishek Vishwakarma Department of CSE, Baderia Global Institute of Engineering and Management (BGIEM), Jabalpur, Madhya Pradesh, India.
Prof. Shivam Tiwari Department of CSE, Baderia Global Institute of Engineering and Management (BGIEM), Jabalpur, Madhya Pradesh, India.
Prof. Ranu Sahu Department of CSE, Baderia Global Institute of Engineering and Management (BGIEM), Jabalpur, Madhya Pradesh, India.
Prashu Jain Department of CSE, Baderia Global Institute of Engineering and Management (BGIEM), Jabalpur, Madhya Pradesh, India.
Sakshi Jain Department of CSE, Baderia Global Institute of Engineering and Management (BGIEM), Jabalpur, Madhya Pradesh, India.

DOI: https://doi.org/10.15680/IJIRCCE.2023.1106071

Keywords: Edge computing, Federated learning, Privacy preservation, Real-time AI, Computational constraints

Abstract

This abstract introduces a federated learning framework designed for edge computing environments, enabling real-time AI applications while safeguarding user privacy. The framework leverages distributed edge devices for collaborative model training without central data aggregation, incorporating privacy-preserving techniques like differential privacy and secure aggregation. Experimental validation demonstrates its effectiveness in maintaining model accuracy and ensuring data confidentiality, supporting its suitability for edge-based AI implementations.