• Abhishek Bhatt
• Anil Kumar Pandey
• Shobhit Sinha

The escalating pace of cloud-based services has upheaved the rationale of resource management mechanisms that are not only efficient but also secure and trust-conscious. The conventional cloud resource management models can be simplified as the optimization of the performance measures formerly under the assumption of a secure environment of execution, which is susceptible to the dynamic security threats and unreliable nodes. In order to overcome these issues, this paper presents a Zero-Trust Federated Learning-Based Deep Framework of Secure and Efficient Cloud Resource Management, which is abbreviated as ZT-FL-MDS-CNet. The framework proposed combines the principles of zero-trust security with federated learning to allow training the models decentrally and in privacy preserving, and to continuously assess the trust in the process of allocating resources. Multi-dimensional deep convolutional network is used to identify the complicated workload patterns and aid in making adaptive decisions. Comprehensive experimental testing versus state-of-the-art cloud resource management models proves that the proposed methodology comes with the best accuracy, precision, recall, and F1-score, and is much lower in terms of execution time and mean absolute error. Moreover, the analysis of trust score evolution demonstrates the gradual convergence in the course of training sessions, which confirms the excellence and dependability of the suggested zero-trust federated structure. The findings prove that federated intelligence with continuously updated trust modeling is an effective solution towards next generation secure cloud resource management.

Cloud Resource Management, Deep Learning, Federated Learning, Resource Allocation Optimization, Secure Cloud Computing, Trust-Aware Systems, Zero-Trust Architecture.

"A Secure Federated Learning Framework with Trust Modeling for Cloud Resource Management", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.b325-b332, January-2026, Available :http://www.jetir.org/papers/JETIR2601149.pdf

"A Secure Federated Learning Framework with Trust Modeling for Cloud Resource Management", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppb325-b332, January-2026, Available at : http://www.jetir.org/papers/JETIR2601149.pdf