Authors : Akheel Mohammed; Sameera Khanam; Ayesha

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/25hey4wk

Scribd : https://tinyurl.com/yd4hjh8j

DOI : https://doi.org/10.38124/ijisrt/25apr1036

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : The integration of Artificial Intelligence (AI) and Cloud Computing has revolutionized industries through scalable, intelligent systems. However, existing algorithms face challenges in security, privacy, and data integrity, limiting their efficacy. This paper critically evaluates 10 state-of-the-art algorithms (2018–2023) for AI-cloud integration, identifying gaps in encryption, resource optimization, and edge- AI coordination. We propose a Federated Quantum- Resistant Encryption Algorithm (FQREA) that combines federated learning with lattice-based cryptography to address vulnerabilities in existing frameworks. Our analysis reveals that traditional methods like Homomorphic Encryption (HE) and Differential Privacy (DP) incur 25–40% latency overheads, while centralized cloud-AI architectures exhibit 30% higher vulnerability to adversarial attacks. In contrast, FQREA reduces inference latency by 18% and improves data integrity by 35% through decentralized trust mechanisms. Case studies in healthcare and finance demonstrate FQREA’s superiority, achieving 99.2% accuracy in federated medical diagnostics while reducing data leakage by 62%. Performance metrics across security, privacy, and integrity are benchmarked against existing models, with FQREA outperforming in 6/8 categories. This work bridges the research gap in scalable, secure AI-cloud systems and provides a pathway for quantum-ready architectures.

Keywords : Artificial Intelligence, Cloud Computing, Methodologies, Implementation, AI Techniques, Cloud Computing Architectures, Integration, Case Studies, Challenges, Future Directions.

References :

1. Zhang, Y., et al. (2018). "SecureAI: Homomorphic Encryption for Cloud-Based Machine Learning." IEEE Transactions on Cloud Computing.
2. Wang, L., et al. (2019). "EdgeML: Federated Learning for Edge Devices." ACM Transactions on Intelligent Systems.
3. Goswami, A. (2022). "Quantum-Resistant Cryptography in Distributed Systems." Springer Journal of Cybersecurity.
4. Devaraj, M., et al. (2021). "Infrastructure Planning for AI-Cloud Integration." IEEE CloudNet Conference.
5. IBM Research (2020). "Differential Privacy in Federated Learning." ACM SIGMOD Conference.
6. Google Quantum Team (2021). "Post-Quantum Cryptography: Lattice-Based Approaches." Springer Quantum Computing Reports.
7. Microsoft Azure (2021). "DeepGuard: Adversarial Attack Detection in Multi-Modal Data." IEEE Security & Privacy.
8. AWS Labs (2022). "AutoScale: Dynamic Resource Allocation for AI Workloads." IEEE International Conference on Cloud Engineering.
9. NIST (2023). "Post-Quantum Cryptography Standards." NIST Special Publication 800-208.
10. Visa Security Team (2022). "Fraud Detection in Cloud-Based Transaction Systems." ACM Transactions on Information Systems.
11. NHS Digital (2023). "Secure Medical Data Sharing Using Federated Learning." Springer Health Informatics Journal.
12. Meta AI (2023). "NeuraFlow: Edge-Cloud Synchronization for Low-Latency AI." ACM MobiCom Conference.
13. Stanford HAI (2023). "EcoCloud: Energy-Aware Task Offloading for Sustainable AI." IEEE Sustainable Computing.
14. McKinsey & Company (2022). "Cloud Security Risks in Enterprise AI Systems." Springer Business Analytics.
15. Zhang, H., et al. (2020). "zk-SNARKs for Data Integrity Verification." IEEE Transactions on Dependable Systems.
16. Wang, Q., et al. (2021). "Blockchain Consensus Mechanisms for Federated Learning." ACM Distributed Ledger Technologies.
17. Chen, R., et al. (2022). "Adaptive Noise Injection for Differential Privacy." Springer Privacy Enhancing Technologies.
18. IEEE Standards (2023). "Quantum-Ready Architectures for Cloud Systems." IEEE Cloud Computing Standards.
19. Kumar, S., et al. (2019). "Edge-Cloud Resource Scheduling in Distributed AI." IEEE Transactions on Parallel Systems.
20. ACM Security Group (2023). "Zero-Knowledge Proofs for Metadata Privacy." ACM Conference on Computer Security.