Privacy-Aware Cross-Domain Intelligence with Federated Generative AI for Regulated Enterprise Systems
Main Article Content
Abstract
Organized business intelligence is increasingly requiring high levels of privacy, security, governmental and conformity requirements. The research paper presents a Privacy-Aware Cross-Domain Intelligence Framework that is a combination of federated learning and generative artificial intelligence that support collaboration between analytics without sensitive data leaving the domain of its origin. The framework provides domain management remote AI environments relating to a controlled federation layer, domains share knowledge through privacy conscious updating of models, policy execution, secure aggregation and authorization. Federated AI generative layer will allow authority domain models to provide expertise to the context and reduce unproblematic liberation of professional data, proprietary data and controlled information. The frameworks applied to enhance the level of trust and accountability include the differentiation in privacy, encryption, tracing provenance, model validation on the receiver and audit. Policy based orchestration layer It is a model sharing, dynamically controlled, participation, authorization, and restrictions on using data, sharing models, workflow management of heterogeneous enterprise environments. The suggested architecture will enhance the sovereignty of the organizational data, secure knowledge synthesis process, anomaly analysis, decision support and the cross-domain intelligence. Framework assessment ensures the privacy protection, effectiveness of communication, usefulness of model, sound governance, scalability and interoperability. The ensuing framework offers a systematic basis behind implementing generative AI within well-controlled, fractionated company systems where the intelligence circulation and privacy protection need to exist simultaneously.
Article Details
Section
How to Cite
References
[1] P. Kairouz et al., “Advances and open problems in federated learning,” Foundations and Trends® in Machine Learning, vol. 14, nos. 1–2, pp. 1–210, 2021, doi: 10.1561/2200000083.
[2] Dave, B. L. (2023). Federated AI frameworks for regulated industries: Cross-domain intelligence for social services, insurance, and industrial operations. International Journal of Research and Applied Innovations, 6(1), 8346-8362.
[3] C. Ren et al., “Advances and open challenges in federated foundation models,” IEEE Communications Surveys & Tutorials, 2025.
[4] T. Fan et al., “Ten challenging problems in federated foundation models,” IEEE Transactions on Knowledge and Data Engineering, 2025.
[5] S. Wei, Y. Zhang, Z. Zhou, T. Zhang, and K. Xu, “FedSM: A practical federated shared mobility system,” Proceedings of the VLDB Endowment, vol. 17, no. 12, pp. 4445–4448, 2024, doi: 10.14778/3685800.3685896.
[6] F. Liu, Z. Zheng, Y. Shi, Y. Tong, and Y. Zhang, “A survey on federated learning: A perspective from multi-party computation,” Frontiers of Computer Science, vol. 18, no. 1, Art. no. 181336, 2024, doi: 10.1007/s11704-023-3282-7.
[7] T. Guo, S. Guo, J. Wang, X. Tang, and W. Xu, “PromptFL: Let federated participants cooperatively learn prompts instead of models—Federated learning in age of foundation model,” IEEE Transactions on Mobile Computing, vol. 23, no. 5, pp. 5179–5194, 2024, doi: 10.1109/TMC.2023.3302410.
[8] J. Hu, D. Wang, Z. Wang, X. Pang, H. Xu, J. Ren, and K. Ren, “Federated large language model: Solutions, challenges and future directions,” IEEE Wireless Communications, 2024.
[9] Z. Wang, Z. Shen, Y. He, G. Sun, H. Wang, L. Lyu, and A. Li, “FLoRA: Federated fine-tuning large language models with heterogeneous low-rank adaptations,” in Proc. 38th Int. Conf. Neural Information Processing Systems (NeurIPS), 2024, pp. 22513–22533.
[10] H. Yang, M. Sui, S. Liu, X. Qian, Z. Zhang, and B. Liu, “Research on key technologies for cross-cloud federated training of large language models,” Academic Journal of Computing & Information Science, vol. 7, no. 11, pp. 42–49, 2024.
[11] J. Jung, H. Jeong, and E. N. Huh, “Federated learning and RAG integration: A scalable approach for medical large language models,” in Proc. 2025 Int. Conf. Artificial Intelligence in Information and Communication (ICAIIC), 2025, pp. 968–973.
[12] R. Ye, R. Ge, F. Yuchi, J. Chai, Y. Wang, and S. Chen, “Leveraging unstructured text data for federated instruction tuning of large language models,” in Federated Learning in the Age of Foundation Models—FL 2024 Int. Workshops, 2025, pp. 119–131.
[13] P. Saha, D. Mishra, F. Wagner, K. Kamnitsas, and J. A. Noble, “FedPIA—Permuting and integrating adapters leveraging Wasserstein barycenters for finetuning foundation models in multi-modal federated learning,” in Proc. 39th AAAI Conf. Artificial Intelligence, 2025, pp. 20228–20236.
[14] X. Liu, T. Pang, and C. Fan, “Federated prompting and chain-of-thought reasoning for improving LLMs answering,” in Proc. 16th Int. Conf. Knowledge Science, Engineering and Management, 2023, pp. 3–11.
[15] T. Che, J. Liu, Y. Zhou, J. Ren, J. Zhou, V. Sheng, H. Dai, and D. Dou, “Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization,” in Proc. 2023 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2023, pp. 7871–7888, doi: 10.18653/v1/2023.emnlp-main.488.