Privacy preserving AI models for decentralized data management in federated information systems
Adeyinka Ogunbajo, Itunu Taiwo, Adefemi Quddus Abidola, Oluwadamilola Fisayo Adediran, Israel Agbo-Adediran · GSC Advanced Research and Reviews · 2025
Federated information systems represent a transformative approach to decentralized data management and privacy-preserving artificial intelligence. This review critically examines the architectural innovations, technological challenges, and emerging paradigms in federated learning and distributed computing environments. By enabling collaborative model training across disparate data sources without direct data sharing, these systems address critical privacy concerns while maintaining computational efficiency. The research synthesizes current implementation strategies across domains such as healthcare, financial services, and edge computing, highlighting the potential of decentralized machine learning architectures. Comparative assessments reveal significant advancements in maintaining data confidentiality while extracting meaningful insights. Persistent challenges include communication overhead, model aggregation complexities, and heterogeneous data distribution problems. The investigation explores advanced cryptographic techniques, secure multi-party computation mechanisms, and differential privacy approaches that underpin federated AI models. Emerging research directions emphasize developing robust standardization protocols, enhancing cryptographic safeguards, and creating adaptive federated learning algorithms capable of dynamically responding to evolving privacy and computational requirements.