Autonomous Threat Intelligence Systems for Dynamic Cyber Defense

Tanaya Jakir; Shakila Sultana; Masrufa Tasnim; Mst Anupa Nasrin Khan; Md Tarake Siddique; Rasel Hossain Babu; Md Himeluzzaman; Tanaya Jakir; Shakila Sultana; Masrufa Tasnim; Mst Anupa Nasrin Khan; Md Tarake Siddique; Rasel Hossain Babu; Md Himeluzzaman

doi:10.15662/IJSRAT.2025.0803006

Autonomous Threat Intelligence Systems for Dynamic Cyber Defense

Tanaya Jakir

MS in Business Analytics, Trine University, USA

Shakila Sultana

Master's in Accounting (M.A), National University, Bangladesh

Masrufa Tasnim

Master of Business Administration (MBA) – Human Resource Management, University of Dhaka, Bangladesh

Mst Anupa Nasrin Khan

Master of Science in Zoology (Entomology Focus), The University of Rajshahi, Bangladesh

Md Tarake Siddique

Master of Science in Information Technology – Data Management & Analytics, Washington University of Science and Technology, Virginia, USA

Rasel Hossain Babu

MS in Cybersecurity (STEM), Bay Atlantic University, Washington, D.C., USA

Md Himeluzzaman

M.Sc. in Information Technology Systems and Management, Washington University of Science and Technology, VA, USA

Abstract

Bustling city streets are filled with the sound of a tiger; the sound of your footsteps as you walk through them leaks into an orchestra that neither has harmony nor rhythm. Lights from sky-scrapers, which are huge and high in the sky at night, pierce into their night's black expanse, sending a strange light cascading around the metropolis. Swarms of people flow through the gaps between skyscrapers, looking like lone figures standing at the hub of an otherwise teeming world. Crowds line the streets, and the air hangs heavy with the smells from both exhaust gases and steaming pots of food being sizzled up, commingling it all. Yet--though the noise is deafening and never-ending--there is still an inherent energy which runs through the city, a non-stop heartbeat that sends it forward into the night.

Five classification algorithms Logistic Regression, Random Forest, Gradient Boosting, Support Vector Classifier, and K-Nearest Neighbors and five regression algorithms Linear Regression, Random Forest Regressor, Gradient Boosting Regressor, XGBoost, and Support Vector Regressor are comprehensively benchmarked. The obtained results show that the best ROC - AUC of 0.822 related to attack spike prediction can be achieved by Logistic Regression, whereas a near-optimal RMSE of 0.422 on attack volume forecasting is reached using Gradient Boosting Regressor and Linear Regression. Correlation analysis reveals a significantly strong correlation between scan_rate and attack_volume_current (r = 0.74), exposing some critical feature importance insight for cyber threat modeling. The paper also analyses the architectural implications, limitations of class-imbalanced datasets, and discusses future directions for deep reinforcement learning-based cyber defense systems

Article Information

Journal	International Journal of Science, Research and Technology
Volume (Issue)	Vol. 8 No. 3 (2025): International Journal of Science, Research and Technology (IJSRAT)
DOI	https://doi.org/10.15662/IJSRAT.2025.0803006
Pages	14262-14272
Published	June 15, 2025
Copyright	All rights reserved
Open Access	This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite	Tanaya Jakir, Shakila Sultana, Masrufa Tasnim, Mst Anupa Nasrin Khan, Md Tarake Siddique, Rasel Hossain Babu, Md Himeluzzaman (%2025). Autonomous Threat Intelligence Systems for Dynamic Cyber Defense. International Journal of Science, Research and Technology , Vol. 8 No. 3 (2025): International Journal of Science, Research and Technology (IJSRAT) , pp. 14262-14272. https://doi.org/10.15662/IJSRAT.2025.0803006

References

[1] A. Milenkoski, M. Vieira, S. Kounev, A. Avritzer, and B. D. Payne, "Evaluating computer intrusion detection systems: A survey of common practices," ACM Computing Surveys, vol. 48, no. 1, pp. 1–41, 2015.
[2] R. Mitchell and I. R. Chen, "A survey of intrusion detection techniques for cyber-physical systems," ACM Computing Surveys, vol. 46, no. 4, pp. 1–29, 2014.
[3] A. L. Buczak and E. Guven, "A survey of data mining and machine learning methods for cyber security intrusion detection," IEEE Communications Surveys & Tutorials, vol. 18, no. 2, pp. 1153–1176, 2016.
[4] D. E. Denning, "An intrusion-detection model," IEEE Transactions on Software Engineering, vol. SE-13, no. 2, pp. 222–232, 1987.
[5] C.-F. Tsai, Y.-F. Hsu, C.-Y. Lin, and W.-Y. Lin, "Intrusion detection by machine learning: A review," Expert Systems with Applications, vol. 36, no. 10, pp. 11994–12000, 2009.
[6] S. Mukkamala, G. Janoski, and A. Sung, "Intrusion detection using neural networks and support vector machines," in Proc. IEEE International Joint Conference on Neural Networks, 2002, pp. 1702–1707.
[7] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
[8] M. H. Bhuyan, D. K. Bhattacharyya, and J. K. Kalita, "Network anomaly detection: Methods, systems and tools," IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 303–336, 2014.
[9] R. Sommer and V. Paxson, "Outside the closed world: On using machine learning for network intrusion detection," in Proc. 31st IEEE Symposium on Security and Privacy, 2010, pp. 305–316.
[10] L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[11] A. A. Diro and N. Chilamkurti, "Distributed attack detection scheme using deep learning approach for Internet of Things," Future Generation Computer Systems, vol. 82, pp. 761–768, 2018.
[12] J. Jacobs, S. Romanosky, B. Edwards, I. Adjerid, and M. Roytman, "Exploit prediction scoring system (EPSS)," arXiv preprint arXiv:1908.04856, 2019.
[13] S. Frei, T. Duebendorfer, G. Ollmann, and M. May, "Understanding the web browser threat: Examination of vulnerable online web browser populations and the insecurity iceberg," ETH Zurich, Tech. Rep., 2008.
[14] D. Bhatt, P. Patel, H. Talsania, J. Patel, R. Vaghela, S. Pandya, K. Modi, and H. Ghayvat, "CNN variants for computer vision: History, architecture, application, challenges and future scope," Electronics, vol. 10, no. 20, p. 2470, 2021.
[15] Y. Mirsky, T. Doitshman, Y. Elovici, and A. Shabtai, "Kitsune: An ensemble of autoencoders for online network intrusion detection," in Proc. Network and Distributed System Security Symposium (NDSS), 2018.
[16]Rasul, I., Tohfa, N. A., Rahman, M., Hossain, I., Zareen, S., & Shakhawat, M. (2023). Quantum Machine Learning for Early Disease Diagnosis: A Systematic Review and Public Health Innovation Perspective. World Journal of Advanced Research and Reviews, 19(01), 1668-1674.
[17] Tohfa, N. A., Hossain, I., Zareen, S., Rasul, I., Hossen, M. S., & Rahman, M. (2021). Adversarial Cognition Machine Learning at the Frontlines of Cyber Warfare. World Journal of Advanced Research and Reviews, 12(02), 722-729.
[18] Alam, A., Gazi, M. S., Abdullah, S. M., Tasnim, M., Himeluzzaman, M., Nabil, M. A., ... & Akter, S. (2021). Quantum-resilient federated intrusion detection: A hybrid quantum classical framework for safeguarding US critical infrastructure in the post-quantum era. International Journal of Advances in Signal and Image Sciences, 7(1), 57-72.
[19]Biswas, B., Chaudhury, T. H., & Mohammad, S. N. A Fast and Scalable Recommender System using Collaborative Filtering Technique in Python Scikit-learn.
[20]Hossain, M. S., Biswas, B., & Rahaman, M. M. (2023). THE ROLE OF ARTIFICIAL INTELLIGENCE IN ENHANCING CYBERSECURITY DEFENSE MECHANISMS. International Journal Of Engineering Technology Research & Management (IJETRM), 7(07), 157-166.