Federated Learning-Enabled Privacy-Preserving Analytics Framework for Multi-Cloud Data Environments
Abstract
Current progress in cloud computing necessitates the constant attention to the Security, Privacy, and Regulatory Compliance. The following paper is a systematic review of recent trends in the use of Federated Learning and Artificial Intelligence to enhance the security of the cloud and maintain user privacy in multi-cloud data models. Based on the findings in the framework of a systematic literature review including 30 studies released since 2020 and until 2024 following the PRISMA 2020 checklist, it is revealed that in case of critical sectors, when incorporated with data anonymization, normalization, and a filter-related approach, Federated Learning drops the risk of privacy invasion by 25% and 40% improves threat detection. Approximately 80 percent of the considered implementations show better privacy preservation, but such problems as communication overhead or latency persist, with 50 percent of studies showing this address. New alternatives like Federated Neural Networks , hybrid networks and cryptographic improvements are studied to the issues. The current paper presents the development of a scalable deployment plan that can be used to implement Federated Learning to support secure, real-time analytics in Industrial Internet Things of Things (IIoT), autonomous systems, and dynamic edge-based environments with the enhancement of privacy-preserving frameworks of robust cloud security.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.