Agentic Machine Learning Framework for Autonomous Cyber Threat Detection and Response in Multi-Cloud Environments
DOI:
https://doi.org/10.21590/Keywords:
Agentic Machine Learning, Autonomous Cybersecurity, Multi-Cloud Security, Threat Detection, Intelligent Agents, Automated Response, Adaptive Cyber DefenseInternational Journal of Technology, Management and Humanities (2026)Abstract
The rapid adoption of multi-cloud computing has created highly distributed enterprise infrastructures in which applications,
workloads, identities, APIs, data, and security controls operate across multiple cloud providers. Although multi-cloud
architectures improve scalability, availability, and flexibility, they also increase security complexity and create opportunities
for sophisticated cyberattacks. Conventional security systems frequently depend on static rules, predefined signatures, and
human-driven investigation, limiting their ability to respond rapidly to dynamic and previously unseen threats. This research
proposes an Agentic Machine Learning Framework for Autonomous Cyber Threat Detection and Response in Multi-Cloud
Environments. The proposed framework integrates machine learning, autonomous intelligent agents, behavioral analytics,
threat intelligence, contextual risk assessment, and automated response orchestration. Distributed agents continuously
monitor cloud infrastructure, network traffic, APIs, identities, workloads, containers, and application behavior. Machine
learning models analyze telemetry to identify anomalies, classify threats, predict attack progression, and determine risk
levels. An agentic decision layer autonomously correlates security events, selects appropriate response strategies, and
coordinates containment actions across heterogeneous cloud platforms. Reinforcement learning and adaptive model
updating enable continuous improvement based on environmental feedback. The methodology emphasizes secure agent
communication, explainable decisions, policy-based governance, human oversight for high-impact actions, and resilience
against adversarial manipulation. Evaluation focuses on detection accuracy, precision, recall, F1-score, false-positive rate,
detection latency, response time, resource consumption, scalability, and autonomous decision effectiveness. The proposed
framework aims to establish an intelligent, scalable, and adaptive foundation for autonomous cybersecurity operations
across complex multi-cloud infrastructures.
References
[1] Choi, Y.-H., Liu, P., Shang, Z., Wang, H., Wang, Z., Zhang, L., Zhou,
J., & Zou, Q. (2020). Using deep learning to solve computer
security challenges: A survey. Cybersecurity, 3, Article 15.
https://doi.org/10.1186/s42400-020-00055-5
[2] Drewek-Ossowicka, A., Pietrołaj, M., & Rumiński, J. (2021).
A survey of neural networks usage for intrusion detection
systems. Journal of Ambient Intelligence and Humanized
Computing, 12, 497–514. https://doi.org/10.1007/s12652-020-
02014-x
[3] Mohile, A. (2026, April). Zero Trust Architectures for Securing
Foundation Model Lifecycles in Enterprise AI Systems. In 2026
3rd International Conference on Research Methodologies
in Knowledge Management, Artificial Intelligence and
Telecommunication Engineering (RMKMATE) (pp. 1-6). IEEE.
[4] Bellundagi, M. (2023). Integrating Machine Learning with
Business Rule Management Systems for Adaptive Enterprise.
International Journal of Research Publications in Engineering,
Technology and Management (IJRPETM), 6(1), 8023-8039.
[5] Hasan, M., Rahman, S. A., Yasin, M., Gazi, M. S., Himeluzzaman,
M., Alam, A., & Jakir, T. (2026). Heart disease prediction using
artificial intelligence algorithms: A comparative study. Vascular
and Endovascular Review, 9(1), 436–445.
[6] Polamarasetty, V. K. (2022). Enterprise SAP application
moderni z at ion for pos t -acqui s i t ion bus ines s
transformation. International Journal of Science,
Research and Technology (IJSRAT), 5(3), 7777–7783.
https://www.ijsrat.com/index.php/ijsrat/issue/view/23
[7] Ramasamy, M. (2025). The synergy of human and AI collaboration
in modern network management. Journal of Computer Science
and Technology Studies, 7(4), 174-180.
[8] Akiri, C. K., Jayabalan, K., Lopes, J., Kareem, S. A., & Tabbassum,
A. (2025, March). Generative AI for real-time cloud security:
Advanced anomaly detection using GPT models. In 2025 IEEE
Conference on Computer Applications (ICCA) (pp. 1-6). IEEE.
[9] Agarwal, S. (2024). Signal Overload in Cloud-Native Observability
Platforms: A Scalable Framework for Telemetry Correlation.
International Journal of Research and Applied Innovations,
7(2), 10466-10473.
[10] Vani, M. (2026). Adaptive agentic AI frameworks for autonomous
task planning and parallel execution. In 2026 International
Artificial Intelligence Technology Conference (AITC) (pp. 78–84).
IEEE. https://doi.org/10.1109/AITC70732.2026.11666578
[11] Bandaru, P. K. (2024). Testing multi-ECU communication
networks in software-defined vehicles. International Journal
of Research and Applied Innovations, 7(4), 11178–11183.
[12] Mole, M. (2025). Artificial intelligence in public safety: Enhancing
prevention and response. Sarcouncil Journal of Engineering
and Computer Sciences, 4(7), 211–217. https://doi.org/10.5281/
zenodo.15818598
[13] Kollu, R. K. (2025). Unlocking Sales Cloud: A Guide to Smarter
Selling in Salesforce. International Journal of Research
Publications in Engineering, Technology and Management
(IJRPETM), 8(5), 12891-12899.
[14] Matrouk, K., V, S., Kumar, S., Bhadla, M. K., Sabirov, M., & Saadh,
M. J. (2023). Deep Learning–based Dynamic User Alignment in
Social Networks. ACM Journal of Data and Information Quality,
15(3), 1-26.
[15] Kargeti, H. (2026, February). Automating Enterprise Vulnerability
Exposure: SCAP-Based Asset-CVE Linkage with Social Signal
Triage for Cyber Defense. In 2026 International Conference on
Artificial Intelligence, Computer, Data Sciences and Applications
(ACDSA) (pp. 1-6). IEEE.
[16] Tyagi, N. (2025). The Compliance Horizon: Anticipating
Regulatory Change in Financial Services and Artificial
Intelligence. International Journal of Research and Applied
Innovations, 8(2), 11227-11232.
[17] Selvarajan, K. (2025). AI-Driven Enterprise Supply ChainIntelligence: A Technical Deep Dive. Journal of Computer
Science and Technology Studies, 7(2), 612-617.
[18] Rajula, A. (2024). Replication-aware caching for low-latency
clinical knowledge retrieval. International Journal of Computer
Technology and Electronics Communication, 7(6), 9997–10007.
[19] Nisar, K. (2025). Why enterprise agent deployments fail: A field
taxonomy. International Journal of Computer Technology and
Electronics Communication, 8(5), 11592-11605.
[20] Pasupuleti, N. S., Kapoor, S., Vedula, J., Sati, M. M., Shamilevna,
G. S., & Khurmat, E. (2025, July). Implementation of a Deep
Learning Model for Real-time Detection of Diabetic Retinopathy
in Primary Care Clinics. In 2025 International Conference on
Information, Implementation, and Innovation in Technology
(I2ITCON) (pp. 1-6). IEEE.
[21] Jain, R. (2018). Beyond stateless: A production architecture
for running distributed databases on Kubernetes at scale.
International Journal of Advanced Engineering Science and
Information Technology (IJAESIT), 1(2), 416–423.
[22] Patel, K. (2026). AI-Powered HACCP Risk Prediction System:
Machine Learning Framework for Predictive Risk Assessment
in HACCP-Based Food Safety Systems. Journal of Intelligent
Decision Making and Information Science, 3(5s), 1956-1978.
[23] Ravichandran, S., & Kandasamy, V. (2025). Optimized Attention
Augmented Residual Convolutional Neural Network with
Fa-Resnet for Fabric Defect Detection. Journal of Control
Engineering and Applied Informatics, 27(4), 3-15.
[24] Awopejo, T. E., Adigun, P. O., Oyekanmi, T. T., Azeez, N. A. A.,
Adekanye, M. A., & Obisesan, A. (2025). Machine learningbased
prediction of magnetic properties from hysteresis
curves: A comparative study of Random Forest, Gradient
Boosting, XGBoost, LightGBM and Support Vector Regressions.
International Journal of Research Publications in Engineering,
Technology and Management, 8(6), 13456–13479.
[25] Vemireddy, S. (2026). Multi-Agent Learning Frameworks for
Scalable Autonomous Business Systems. International Journal
of Research and Applied Innovations, 9(2), 131-136.
[26] Hashmi, H., & Srikanth, V. (2023, November). Combining Neural
Networks to Recognize Offline Digits & Words by Training the
Model Using Keras. In 2023 3rd International Conference on
Advancement in Electronics & Communication Engineering
(AECE) (pp. 694-697). IEEE.
[27] Pothuri, M. K. (2025). How modern BI stacks power smarter,
faster decision-making in public health care—Blueprint of a
modern BI architecture: Designing for scale, speed, and selfservice.
International Journal for Multidisciplinary Research, 7(5).
https://doi.org/10.36948/ijfmr.2025.v07i05.57947
[28] Padmanabham, S. (2024). Intelligent security architecture for
risk and compliance. International Journal of Science, Research
and Technology (IJSRAT), 7(1), 11373–11380.
[29] Chaturvedi, V., Narra, R., & Chintagunta, S. K. (2026). Applied AI
engineering for developers: Building intelligent applications
at scale. Wissira Press. https://doi.org/10.63345/WP-978-93-
7559-963-0
[30] Sasikumar, B., Venkatasalam, K., & Rajendran, P. (2024). Induction
motor fault detection and classification using rcnn and surf
based machine learning algorithms and infrared thermography.
Scientia Iranica.
[31] Sharma, K., Singhal, A. B., karthik Chundi, V. R., & Arveti, S. (2026,
February). Analyzing Interdependencies Between IoT Data
Integration Capabilities and Real-Time Operational Decision-
Making: A DEMATEL Approach. In 2026 5th International
Conference on Innovative Practices in Technology and
Management (ICIPTM) (pp. 1-5). IEEE.
[32] Badam, L. R. (2023). Explainable AI framework for real-time
financial fraud detection in banking systems. International
Journal of Emerging Trends in Engineering and Management
Research, 8(2), 13241–13251.
[33] Balaraman, N. K., Patel, K., & Reddy, N. (October 2025). Smart
Water Management: Integrating PLC and SCADA Technologies
for Sustainable Urban Infrastructure. In Proceedings of the 22nd
International Conference on Informatics in Control, Automation
and Robotics (ICINCO) (Vol. 1, pp. 305–312). SciTePress.
[34] Anwar, S. B., Rimon, R. H., Hoque, M. J., Zubair, S. M., & Fatema,
T. (2026). Ransomware prediction and detection in healthcare
Networking using AI. Journal of Computer Science and
Technology Studies, 8(8), 33-57.
[35] Mirani, A. (2026). Designing AI-native financial systems:
Architecture patterns for intelligent enterprise platforms.
IPHO-Journal of Advance Research in Science and Engineering,
4(4), 21–33.
[36] Attaluri, V., & Mudunuri, L. N. R. (2025). Generative AI for
creative learning content creation: project-based learning and
art generation. In Smart Education and Sustainable Learning
Environments in Smart Cities (pp. 239-252). IGI Global Scientific
Publishing.
[37] Tarakampet, S., Tatavarthi, S., & Puvvula, G. (2026, July). The Role
of AI and Machine Learning in Next-Generation Governance,
Risk, and Compliance (GRC) Platforms. In 2026 Seventeenth
International Conference on Ubiquitous and Future Networks
(ICUFN) (pp. 507-512). IEEE.
[38] Natarajan, A., Narra, S. L., Kanimetta, D. K., Dubey, P., &
Potharalanka, L. (2025). Modernizing digital infrastructure for
intelligent systems. International Journal of Computing and
Engineering, 7(10), 111. CARI Journals USA LLC.
[39] Mali, R. K. (2026, July). AI-Driven Cloud-Native Banking
Platforms: A Scalable Architecture for Real-Time Financial
Services. In 2026 International Conference on Intelligent and
Sustainable AI Systems (ICOSAAS) (pp. 749-756). IEEE.
[40] Alhajri, M. I., & Alotaibi, M. (2022). Machine learning for energyresource
allocation, workflow scheduling and live migration
in cloud computing: State-of-the-art survey. Sustainable
Computing: Informatics and Systems, 36, 100780. https://doi.
org/10.1016/j.suscom.2022.100780
