Privacy-Aware AI in cloud-telecom convergence: A federated learning framework for secure data sharing
Adedeji Ojo Oladejo, Michael Adedayo Adebayo, David Olufemi, Eunice Kamau, Deligent Bobie-Ansah, Daniel E. Williams
Abstract
With the increasing demand for integrated cloud and telecommunications (cloud-telecom convergence), the need for privacy-preserving artificial intelligence (AI) models has never been more urgent. Federated learning (FL) has emerged as a powerful framework that facilitates secure and privacy-aware machine learning models, without the need to share raw data between entities. This paper explores the role of federated learning in ensuring secure data sharing within cloud-telecom convergence, with a focus on privacy preservation. We discuss the fundamental concepts of privacy-aware AI, cloud-telecom integration, and federated learning. Moreover, we highlight the challenges, key research directions, and practical implementations of these technologies to achieve secure and scalable data sharing in 5G/6G environments. Through a systematic review of recent advances and future trends, we demonstrate the promise of federated learning in enabling privacy-preserving AI solutions in this domain.