Secure RAG-Agent Framework for Multi-Cloud Service Management
Keywords:
Enterprise service management, multi-cloud architecture, AI agents, security, cloud federation A hybrid cloud-based service architecture is envisaged, comprising the implementation and operation of enterprise services internally at the organization level, together with hosting additional services externally in the clouds of other organizations. This requires a secure retrieval-augmented AI agent framework, providing subject matter expertise, scalable service delivery, and adaptive behavior. The secure retrieval-augmented AI agent framework supports enterprise service management in a trusted multi-cloud environment. This includes federation, enabling secure inter-cloud communications enabled by zero-knowledge proof technology. Distributed retrieval-augmented AI agents are deployed throughout the multi-cloud environment to provide domain-specific expertise in managing different types of enterprise services. Security and privacy controls allow organization-wide management of sensitive user and enterprise query data and information so that this data can be accessed only in an encrypted format by trusted agents that have the appropriate decryption keAbstract
Artificial intelligence (AI) has made remarkable strides in the form of robust AI models capable of comprehensively addressing numerous human-created challenges and performing sophisticated tasks. Service-oriented at their core, these AI models require access to mountain-sized knowledge bases, which is being offered as a service by cloud and edge service providers. However, these models operate like a black box, making it impossible to correctly validate their decisions. Recent attempts to fuse the rich semantic knowledge of knowledge graphs with neural word embeddings fall short of addressing the concerns of security and privacy.
This paper proposes a novel Secure Retrieval-Augmented AI Agent (SRA2I) framework that can adapt to solving human-desired tasks while ensuring data security and privacy. The knowledge base supporting the reasoning agent core in the SRA2I framework can execute complex service-oriented requests across multi-cloud deployments. Consequently, intelligent decision-making pipelines that guide human-computer interaction can be designed and deployed in a multi-cloud federated environment that pays attention to compliance and governance checkpoints. Based on insightful synthesis, the discussion then focuses on a thorough evaluation of the retrieval and reasoning ability of a retrieval-augmented visual-chatbot implementation.
Downloads
References
1. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M.-W. (2020). Retrieval augmented language model pre-training. Proceedings of the 37th International Conference on Machine Learning, 3929–3938.
2. Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769–6781.
3. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., & Riedel, S. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
4. Davuluri, P. S. L. (2023). AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems. AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems (December 15, 2023).
5. Tomarchio, O., Calcaterra, D., & Di Modica, G. (2020). Cloud resource orchestration in the multi-cloud landscape: A systematic review of existing frameworks. Journal of Cloud Computing, 9, Article 49.
6. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N., Chen, A., Creel, K., Davis, J. Q., Demszky, D., … Liang, P. (2021). On the opportunities and risks of foundation models. arXiv.
7. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 874–880.
8. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J.-B., Damoc, B., Clark, A., de Las Casas, D., Guy, A., Menick, J., Ring, R., Hennigan, T., Huang, S., Maggiore, A., Jones, C., Cassirer, A., … Sifre, L. (2022). Improving language models by retrieving from trillions of tokens. Proceedings of the 39th International Conference on Machine Learning, 2206–2240.
9. Izacard, G., Lewis, P., Lomeli, M., Hosseini, L., Petroni, F., Schick, T., Dwivedi-Yu, J., Joulin, A., Riedel, S., & Grave, E. (2023). Atlas: Few-shot learning with retrieval augmented language models. Journal of Machine Learning Research, 24, 1–43.
10. Kolla, S. K., & Mangalampalli, B. M. (2024). Edge-Based Deep Learning Systems for Point-of-Care Diagnostic Intelligence. Journal of Neonatal Surgery, 13(1), 2387-2399.
11. Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2024). Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12, 157–173.
12. Shi, W., Min, S., Yasunaga, M., Seo, M., Lewis, M., Zettlemoyer, L., & Yih, W.-t. (2024). REPLUG: Retrieval-augmented black-box language models. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics.
13. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv.
14. Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., … Wen, J.-R. (2023). A survey of large language models. arXiv.
15. Inala, R. (2023). AI-powered investment decision support systems: Building smart data products with embedded governance controls. Journal for ReAttach Therapy and Developmental Diversities, 6(10), 2251-2266.
16. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations.
17. Schick, T., Dwivedi-Yu, J., Dessi, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36.
18. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., Awadallah, A. H., White, R. W., Burger, D., & Wang, C. (2024). AutoGen: Enabling next-gen LLM applications via multi-agent conversation. Proceedings of the 2024 Conference on Language Modeling.
19. Zhan, Q., Liang, Z., Ying, Z., & Kang, D. (2024). InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents. Findings of the Association for Computational Linguistics: ACL 2024, 10471–10506.
20. Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., & Fritz, M. (2023). Not what you've signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection. Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 79–90.
21. Kolla, S. K., & Reddy, V. A. R. (2024). Evaluating Cloud-Native vs. Hybrid Architectures for Health Benefit Administration Systems. International Journal of Medical Toxicology and Legal Medicine, 27(5), 1042-1053.
22. Saad-Falcon, J., Khattab, O., Potts, C., & Zaharia, M. (2024). ARES: An automated evaluation framework for retrieval-augmented generation systems. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 338–354.
23. Ram, O., Kirstein, M., Tenenboim-Chekroun, F., Tenenboim-Chekroun, E., & Berant, J. (2023). In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics, 11, 1316–1331.
24. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. International Conference on Learning Representations.
25. Shi, F., Chen, Y., Misra, K., Scales, N., Roelofs, R., & Chi, E. (2024). RAGTruth: A hallucination corpus for developing trustworthy retrieval-augmented language models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.
26. Gottimukkala, V. R. R. (2024). Federated Learning Approaches for Fraud Detection in International Payment Systems. https://www. jisem-journal. com/download/118_JISEM. pdf.
27. Yan, S.-Q., Gu, J.-C., Zhu, Y., & Ling, Z.-H. (2024). Corrective retrieval augmented generation. arXiv.
28. Chen, J., Lin, J., & Yang, L. (2024). RAGCache: Efficient knowledge caching for retrieval-augmented generation. Proceedings of the ACM Web Conference 2024.
29. Gao, L., Ma, X., Lin, J., & Callan, J. (2023). Precise zero-shot dense retrieval without relevance labels. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.
30. Khattab, O., Santhanam, K., Li, X. L., Hall, K. B., Liang, P., & Potts, C. (2023). Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive NLP. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.
31. Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., & Hajishirzi, H. (2023). When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.
32. Min, S., Lewis, P., Hajishirzi, H., & Zettlemoyer, L. (2022). Rethinking the role of demonstrations: What makes in-context learning work? Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 11048–11064.
33. Ovadia, Y., Koyejo, S., Gat, I., Lee, T., Carmon, Y., & Taori, R. (2023). Fine-tuning or retrieval? Comparing knowledge adaptation approaches for language models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.
34. Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., & Wei, F. (2023). Text embeddings by weakly-supervised contrastive pre-training. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.
35. Liu, J., Lin, J., & Yang, L. (2023). Retrieval-augmented generation for large language models: A systematic survey. Journal of Artificial Intelligence Research.
36. Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Dwivedi-Yu, J., & Scialom, T. (2023). Augmented language models: A survey. Transactions on Machine Learning Research.
37. Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology.
38. Shinn, N., Cassano, F., Labash, B., Gopinath, A., Narasimhan, K., & Yao, S. (2023). Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36.
39. Kolla, T. (2024). Graph Neural Networks for HCC Risk Adjustment and Interoperability. International Journal of Science, Research and Technology, 7(6), 13244-13255.
40. Wang, Z., Mao, S., Wu, W., Ge, T., Wei, F., & Huang, W. (2023). Unleashing the power of large language models for reasoning and decision making. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.
41. Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023). Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36.
42. Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., & Schmidhuber, J. (2024). MetaGPT: Meta programming for multi-agent collaborative framework. International Conference on Learning Representations.
43. Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024). Large language model based multi-agents: A survey of progress and challenges. Proceedings of the 33rd International Joint Conference on Artificial Intelligence.
44. Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Qin, S., Wang, R., Gui, J., Zhang, D., Qiu, L., Li, F., & others. (2023). The rise and potential of large language model based agents: A survey. arXiv.
45. Wang, J., Shi, Z., & others. (2023). Large language models as autonomous agents: A survey. Artificial Intelligence Review.
46. Alizadeh, M., Kubota, T., & others. (2023). Large language models for cloud computing: A survey. IEEE Access.
47. Tomarchio, O., Calcaterra, D., & Di Modica, G. (2020). Multi-cloud resource orchestration: A systematic review of existing approaches. Journal of Cloud Computing, 9.
48. Deep, S., Akhtar, M. S., & others. (2023). Deep learning approach to security enforcement in cloud workflow orchestration. Journal of Cloud Computing, 12, Article 10.
49. Voruganti, K. K. (2024). Orchestrating multi-cloud environments for enhanced flexibility and resilience. Journal of Technology and Systems.
50. Srikanth, N. (2024). Secure multi-cloud DevOps architecture with AI-driven threat detection and automated infrastructure resilience. International Journal of Technology, Management and Humanities.
51. Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024). Retrieval-augmented generation for AI-generated content: A survey. ACM Computing Surveys.
Additional Files
Published
Data Availability Statement
None
