International Journal of Telecommunications & Emerging Technologies Review Article
Autonomous Incident Response Using AI Agents
Abstract
Cybersecurity incident response increasingly operates under conditions of high alert volume, complex infrastructure, and limited analyst time. Artificial Intelligence (AI) agents offer a practical way to automate selected response activities because an agent can maintain goals, use security tools, analyze evidence, coordinate with other agents, and choose actions over multiple steps. This review presents a conceptual framework for autonomous incident response using AI agents while emphasizing bounded autonomy rather than unrestricted machine control. The proposed architecture contains triage, investigation, threat-intelligence, response-planning, policy/critic, and execution functions connected through a shared incident state, audit trail, and human approval path. It explains how agents can support alert prioritization, evidence collection, attack-technique mapping, containment planning, recovery verification, and post-incident learning. Autonomy is matched to action consequence, confidence, asset criticality, and rollback capability. The framework is aligned with Electrical and Electronics (E/E) Engineering through network interfaces, secure gateways, edge devices, hardware roots of trust, industrial and Internet of Things (IoT) systems, power continuity, sensing, and cyber-physical infrastructure. Major challenges include hallucination, incomplete context, adversarial manipulation, tool misuse, privacy, explainability, and evaluation under realistic attack conditions. A phased deployment strategy is recommended in which AI first observes and recommends, then progresses toward low-risk automated response only after repeated validation.
Keywords
References (16)
- 1. Nelson A, Rekhi S, Souppaya M, Scarfone K. Incident response recommendations and considerations for cybersecurity risk management. NIST special publication. 2025 Apr;800 doi:10.6028/NIST.SP.800-61r3.
- 2. Pascoe CE. Public draft: The NIST cybersecurity framework 2.0. National Institute of Standards and Technology. 2023 Aug 7 doi:10.6028/NIST.CSWP.29.ipd.
- 3. Mink D, Simpson A, Bagui SS, Bagui SC. RandomForestNN Classification for Adversarial AI Black-Box Techniques on MITRE ATT&CK Labeled Data. Electronics. 2026 Jun 12;15(12):2598 doi:10.3390/electronics15122598.
- 4. Romano J, Sparrell D. Open command and control (OpenC2) language specification version 1.0. OASIS Committee Specification. 2019 Nov;1.
- 5. Applebaum A, Dennler C, Dwyer P, Moskowitz M, Nguyen H, Nichols N, Park N, Rachwalski P, Rau F, Webster A, Wolk M. Bridging automated to autonomous cyber defense: Foundational analysis of tabular q-learning. InProceedings of the 15th ACM Workshop on Artificial Intelligence and Security 2022 Nov 11 (pp. 149-159) doi:10.1145/3560830.3563732.
- 6. Ren S, Jin J, Niu G, Liu Y. ARCS: Adaptive reinforcement learning framework for automated cybersecurity incident response strategy optimization. Applied Sciences. 2025 Jan 19;15(2):951 doi:10.3390/app15020951.
- 7. Vyas S, Mavroudis V, Burnap P. Towards the deployment of realistic autonomous cyber network defence: A systematic review. ACM Computing Surveys. 2025 Aug 30;58(1):1-36 doi:10.1145/3729213.
- 8. Loevenich J, Adler E, Huerten T, Lopes RR. Design and evaluation of an Autonomous Cyber Defence agent using DRL and an augmented LLM. Computer Networks. 2025 May 1;262:111162 doi:10.1016/j.comnet.2025.111162.
- 9. Morris A, Procter R, Wallbank C. Evaluating Reinforcement Learning Agents for Autonomous Cyber Defence. Applied AI Letters. 2025 Oct;6(3):e125 doi:10.1002/ail2.125.
- 10. Srinivas S, Kirk B, Zendejas J, Espino M, Boskovich M, Bari A, Dajani K, Alzahrani N. AI-augmented SOC: A survey of LLMs and agents for security automation. Journal of Cybersecurity and Privacy. 2025 Nov 5;5(4):95 doi:10.3390/jcp5040095.
- 11. Xu H, Wang S, Li N, Wang K, Zhao Y, Chen K, Yu T, Liu Y, Wang H. Large language models for cyber security: A systematic literature review. ACM Transactions on Software Engineering and Methodology. 2025 Sep doi:10.1145/3769676.
- 12. Wang M, Dechene R. Multi-agent actor-critics in autonomous cyber defense. arXiv preprint arXiv:2410.09134. 2024 Oct 11. doi:10.48550/arXiv.2410.09134.
- 13. Alqahtani H, Ahuja P. Secure autonomous cyber defense with LLM agents: A systematic review of autonomy, tool-augmented reasoning, and governance constraints. Computers and Electrical Engineering. 2026 Jul 1;135:111184 doi:10.1016/j.compeleceng.2026.111184.
- 14. AI N. Artificial intelligence risk management framework (AI RMF 1.0). URL: https://nvlpubs. nist. gov/nistpubs/ai/nist. ai. 2023 Jan;1(0):0-1. doi:10.6028/NIST.AI.100-1.
- 15. Rose S, Borchert O, Mitchell S, Connelly S. Zero trust architecture. NIST special publication. 2020 Aug 10;800(207):1-52. doi:10.6028/NIST.SP.800-207.
- 16. Lohn A, Knack A, Burke A, Jackson K. Autonomous Cyber Defense. A roadmap from lab to ops. Online. Centre for Emerging Technology and Security (CETaS) at The Alan Turing Institute. 2023 Jun. doi:10.51593/2022CA007.