Federated Deep Learning-Based Zero-Trust Architecture for Intelligent Intrusion Detection in Multi-Cloud Systems
Abstract
The rapid adoption of multi-cloud environments has transformed modern digital infrastructures by improving scalability, flexibility, and service availability. However, the distributed nature of multi-cloud systems introduces significant cybersecurity challenges, including unauthorized access, lateral movement attacks, data breaches, and sophisticated network intrusions. Traditional perimeter-based security mechanisms often struggle to provide effective protection in such dynamic and heterogeneous environments. To address these limitations, this study proposes a federated deep learning-based zero-trust architecture for intelligent intrusion detection in multi-cloud systems. The proposed framework integrates the principles of zero-trust security, where every user, device, and application is continuously verified, with federated learning that enables collaborative model training without exposing sensitive organizational data. Deep learning models deployed across multiple cloud domains learn local intrusion patterns and share model parameters rather than raw data, thereby preserving privacy and regulatory compliance. The architecture incorporates continuous authentication, behavioral monitoring, anomaly detection, and decentralized intelligence to identify both known and emerging cyber threats in real time. Furthermore, the framework enhances resilience against data leakage, model poisoning, and insider attacks through secure aggregation and trust evaluation mechanisms. The…
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.