| Title | Federated Learning for Privacy-Preserving Artificial Intelligence in Distributed Systems |
| Research Area | Privacy-Preserving AI |
| Abstract | The increasing reliance on data-driven Artificial Intelligence (AI) systems has raised significant concerns regarding data privacy, security, and regulatory compliance. Traditional centralized machine learning approaches require large volumes of data to be collected and stored in centralized servers, increasing the risk of data breaches and privacy violations. Federated Learning (FL) has emerged as a decentralized machine learning paradigm that enables collaborative model training without sharing raw data. This paper presents a comprehensive study of federated learning, focusing on its architecture, algorithms, applications, and challenges. The proposed framework demonstrates how federated learning can preserve data privacy while achieving high model accuracy across distributed environments. Experimental findings indicate that federated learning achieves comparable performance to centralized models while significantly reducing privacy risks. The paper also discusses challenges such as communication overhead, data heterogeneity, and system scalability. |
| Keywords | Federated Learning, Privacy-Preserving AI, Distributed Systems, Machine Learning, Data Security, Edge Computing |
| Paper Status | Published |
| Volume | 2 |
| Issue | 2 |
| Published On | 04/03/2026 |
| Published File |
IJSRTD_4876.pdf
|