DOI:
https://doi.org/10.64539/msts.v2i1.2026.420Keywords:
AI Firewall, Generative AI, Large Language Models (LLMs), AIOps Security, eBPF, Adversarial ResilienceAbstract
The rapid integration of Generative AI into Automated IT Operations (AIOps) has introduced "AI Sentinels", an autonomous agents capable of managing critical infrastructure. However, these systems introduce a novel attack surface evidenced in inference-time adversarial manipulations such as prompt injection and jailbreaking. While existing security paradigms protect network perimeters, they fail to safeguard the internal logic of AI agents, creating a research gap in runtime defense for autonomous infrastructure controllers. This study aims to develop a multi-layered, defense-in-depth architecture to neutralize these threats. The proposed system integrates three layers: an Intent Validation Engine (Layer 1) using semantic analysis, a Secure Sandbox (Layer 2) utilizing eBPF-based kernel monitoring within a digital twin, and a Static Analysis module (Layer 3) for infrastructure-as-code (IaC) compliance. Key findings indicate that while single-layer defenses achieve an Adversarial Success Rate (ASR) of 32–68%, the proposed multi-layered approach reduces the ASR to near-zero (0.2% in robust testing), maintaining an F1-score of 0.990. Despite the complexity of the pipeline, the system achieves a mean operational latency of 48.2ms on enterprise-grade hardware (NVIDIA A100). These implications suggest that runtime behavioral verification is essential for the safe deployment of LLMs in privileged environments, providing a foundational framework for resilient AIOps.
References
[1] A. Sekar, "AIOps: Transforming Management of Large-Scale Distributed Systems," European Journal of Computer Science and Information Technology, vol. 13, no. 5, pp. 1–17, Apr. 2025. https://doi.org/10.37745/ejcsit.2013/vol13n5117.
[2] S. T. Erukude, S. R. Veluru, and V. C. Marella, "Agentic AI: The Rise of Autonomous Intelligent Agents in the Era of LLMs," SSRN Electronic Journal, 2025. https://doi.org/10.2139/ssrn.5403441.
[3] A. Dehghantanha, S. Homayoun, " SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy," arXiv preprint arXiv:2603.22928, 2023. https://doi.org/10.48550/arXiv.2603.22928.
[4] K. Chlasta, "The Dual-Use Dilemma of Generative Artificial Intelligence in Cybersecurity: Navigating the Explosive Growth in Offensive and Defensive Applications," Security and Defence Quarterly, vol. 52, no. 4, 2024. https://doi.org/10.35467/sdq/217364.
[5] P. Alaeifar, S. Pal, Z. Jadidi, M. Hussain, and E. Foo, "Current Approaches and Future Directions for Cyber Threat Intelligence Sharing: A Survey," Journal of Information Security and Applications, vol. 83, Art. no. 103786, 2024. https://doi.org/10.1016/j.jisa.2024.103786.
[6] G. Zizzo, G. Cornacchia, K. Fraser, M. Z. Hameed, A. Rawat, B. Buesser, M. Purcell, P.-Y. Chen, P. Sattigeri, and K. Varshney, "Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs," arXiv preprint arXiv:2502.15427, 2024. https://doi.org/10.48550/arXiv.2502.15427.
[7] T. Abdiukov, "Automated Security Testing in DevSecOps Pipelines: Integrating AI-Based Vulnerability Discovery and Compliance Validation," World Journal of Advanced Research and Reviews, vol. 22, no. 1, pp. 2083–2093, Apr. 2024. https://doi.org/10.30574/wjarr.2024.22.1.1083.
[8] K. I. Mohammed, B. Shanmugam, and J. El-Den, "Evolution of DevSecOps and Its Influence on Application Security: A Systematic Literature Review," Technologies, vol. 13, no. 12, Art. no. 548, 2025. https://doi.org/10.3390/technologies13120548.
[9] E. A. Khadem and A. Movaghar, "From Challenges to Metrics: An LLM-Driven DevOps Recommendation System Grounded in Evidence-Based Mappings," Array, vol. 28, Art. no. 100547, 2025. https://doi.org/10.1016/j.array.2025.100547.
[10] P. K. Thota, "A Generative AI Framework for Autonomous Infrastructure Management in Cloud Operations," International Scientific Journal of Engineering and Management (ISJEM), vol. 3, no. 10, pp. 1–12, 2024. https://isjem.com/download/a-generative-ai-framework-for-autonomous-infrastructure-management-in-cloud-operations/.
[11] K. A. Singh and A. Choudhry, "AI-Powered Strategies for Cloud Infrastructure Management," in Proc. 4th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0, 2025. https://doi.org/10.1109/OTCON65728.2025.11070393.
[12] S. Vissarapu, "Generative AI in Cloud-Native Development: Automating Code, Configs, and Deployment," European Journal of Computer Science and Information Technology, vol. 13, no. 38, pp. 145–156, 2025. https://doi.org/10.37745/ejcsit.2013/vol13n38145156.
[13] P. Khlaisamniang, P. Khomduean, K. Saetan, and S. Wonglapsuwan, "Generative AI for Self-Healing Systems," in Proc. 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), 2023. https://doi.org/10.1109/iSAI-NLP60301.2023.10354608.
[14] T. A. K. Manne, "Generative AI for Cloud Infrastructure Decision-Making and Self-Healing Systems," Journal of Artificial Intelligence & Cloud Computing, vol. 3, no. 3, pp. 1–5, 2024. https://doi.org/10.47363/JAICC/2024(3)456.
[15] S. R. Challa, "Autonomous Cloud Engineering: The Rise of Self-Healing AWS Infrastructure Using AI and Event-Driven Automation," World Journal of Advanced Engineering Technology and Sciences, vol. 15, no. 2, pp. 2576–2587, 2025. https://doi.org/10.30574/wjaets.2025.15.2.0810.
[16] A. Al Adily, "Automating Incident Response with AI: Investigating How Generative AI Can Streamline and Automate Incident Response Processes," International Journal of Advances in Engineering and Management (IJAEM), vol. 6, no. 12, pp. 569–575, 2024. https://doi.org/10.35629/5252-0612569575.
[17] A. Patel, P. Pandey, H. Ragothaman, R. Molleti, and D. R. Peddinti, "Generative AI for Automated Security Operations in Cloud Computing," in Proc. 4th IEEE International Conference on AI in Cybersecurity (ICAIC), 2025, pp. 1–7. https://doi.org/10.1109/ICAIC63015.2025.10849302.
[18] A. Zaboli and J. Hong, "Generative AI for Critical Infrastructure in Smart Grids: A Unified Framework for Synthetic Data Generation and Anomaly Detection," arXiv preprint arXiv:2508.08593, 2025. https://doi.org/10.48550/arXiv.2508.08593.
[19] Y. Usman, A. Upadhyay, P. Gyawali, and R. Chataut, "Is Generative AI the Next Tactical Cyber Weapon For Threat Actors? Unforeseen Implications of AI Generated Cyber Attacks," arXiv preprint arXiv:2408.12806, 2024. https://doi.org/10.48550/arXiv.2408.12806.
[20] A. Enemosah and O. G. Ifeanyi, "Cloud Security Frameworks for Protecting IoT Devices and SCADA Systems in Automated Environments," World Journal of Advanced Research and Reviews, vol. 22, no. 3, pp. 2232–2252, 2024. https://doi.org/10.30574/wjarr.2024.22.3.1485.
[21] S. Jarugula, "AI-Driven Real-Time Transaction Monitoring and Automated Threat Response: Revolutionizing Payment Security," International Journal on Science and Technology, vol. 16, no. 1, 2025. https://doi.org/10.71097/IJSAT.v16.i1.2718.
[22] S. Dixit, "Generative AI-Powered Document Processing at Scale with Fraud Detection for Large Financial Organizations," International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 10, no. 5, pp. 1038–1065, 2024. https://doi.org/10.32628/CSEIT2410612455.
[23] A. Kuthuru, "Responsible AI in Database Systems: Governance Frameworks for Generative AI Data Access," World Journal of Advanced Research and Reviews, vol. 26, no. 2, pp. 3017–3026, 2025. https://doi.org/10.30574/wjarr.2025.26.2.1942.
[24] P. Koopman and M. Wagner, "Challenges in Autonomous Vehicle Testing and Validation," SAE International Journal of Transportation Safety, vol. 4, no. 1, pp. 15–24, 2016. https://doi.org/10.4271/2016-01-0128.
[25] N. Rani, B. Saha, and S. K. Shukla, "A Comprehensive Survey of Automated Advanced Persistent Threat Attribution: Taxonomy, Methods, Challenges and Open Research Problems," Journal of Information Security and Applications, vol. 92, Art. no. 104076, 2025. https://doi.org/10.1016/j.jisa.2025.104076.
