Submit your papersSubmit Now
For Enquiries: [email protected]
IIARD LogoIIARD
📄 Download Paper

A Model for Real-Time Classification of Data Exfiltration Attacks in Enterprise Networks

I. M. Ossai, E. O. Bennett, D. Matthias, V. I. E. Anireh

Abstract

The real-time classification of network attack types remains one of the most critical and underserved challenges in enterprise cybersecurity. As adversaries deploy increasingly sophisticated techniques, including covert channels, botnet-controlled exfiltration, and low-and- slow data theft, traditional detection mechanisms struggle to provide the granularity and speed that modern enterprise environments demand. This paper presents an Adaptive Support Vector Machine -Based Classification Module designed for the real-time identification and categorization of data exfiltration attacks in enterprise networks. The proposed module operates within a hybrid three-tier security architecture that also includes a Random Forest access control mechanism and a Mamdani Fuzzy Inference-based detection engine. By combining a Fuzzy Exfiltration Score derived from key network flow features with a linear-kernel SVM classifier, the system distinguishes five distinct traffic categories which include Benign, Insider Threat, External Threat, Data Breach, and Botnet Activities. The model was trained and evaluated using the CICIDS-2017 dataset and the CERT Insider Threat Dataset. Experimental results demonstrate a classification accuracy of 95.45%, a True Positive Rate of 96.77%, precision of 96.77%, and an F1-Score of 96.77%. The Matthews Correlation Coefficient of approximately 92% further confirms the model’s robustness across imbalanced class distributions. These findings establish the proposed SVM-based classification module as a viable, interpretable, and deployable component for real-time cyber threat response in enterprise network environments.

Keywords

Machine LearningSupport Vector MachineReal-Time Attack ClassificationData Exfiltration.

References

[1] O. Afolalu and M. S. Tsoeu, 'Enterprise networking optimization: a review of challenges, solutions, and technological interventions,' Future internet, vol. 17, p. 133, 2025. [2] M.-H. Chung, Y. Yang, L. Wang, G. Cento, K. Jerath, A. Raman, et al., 'Implementing data exfiltration defense in situ: a survey of countermeasures and human involvement,' acm computing surveys, vol. 55, pp. 1-37, 2023. [3] Y. Ozery, A. Nadler, and A. Shabtai, 'Information Based Heavy Hitters for Real-Time DNS Data Exfiltration Detection,' in NDSS, 2024. [4] Y. Wang, T. Sun, S. Li, X. Yuan, W. Ni, E. Hossain, et al., 'Adversarial attacks and defenses in machine learning-empowered communication systems and networks: A contemporary survey,' IEEE Communications Surveys & Tutorials, vol. 25, pp. 2245- 2298, 2023. [5] A. Yang, C. Lu, J. Li, X. Huang, T. Ji, X. Li, et al., 'Application of meta-learning in cyberspace security: A survey,' Digital Communications and Networks, vol. 9, pp. 67-78, 2023. [6] M. Jabardi, 'Support vector machines: Theory, algorithms, and applications,' Infocommunications Journal, vol. 17, pp. 66-75, 2025. [7] A. K. Jain, 'Comparative Analysis of Signature-Based and Anomaly-Based IDS,' International Journal of Advanced Research in Computer Science and Engineering (IJARCSE), vol. 1, pp. (25-31), 2025. [8] I. N. Davies, O. E. Taylor, V. I. E. Anireh, and E. O. Bennett, 'Adaptive Hybrid Case- Based Neuro-Fuzzy Model for Intrusion Detection and Prevention for Smart Home Network,' International Journal of Computer Sciences and Engineering, vol. 10, pp. 01- 10, 2024. [9] B. Sabir, F. Ullah, M. A. Babar, and R. Gaire, 'Machine learning for detecting data exfiltration: A review,' ACM Computing Surveys , vol. 54, pp. 1-47, 2021. [10] R. Genuer, J.-M. Poggi, and C. Tuleau-Malot, 'Variable selection using random forests,' Pattern recognition letters, vol. 31, pp. 2225-2236, 2010. [11] G. Vashishtha, S. Chauhan, and R. Kumar, 'Fuzzy-based fault diagnosis in rotating machines: A comprehensive review,' Measurement, vol. 218, p. 113257, 2023. [12] A. R. Hakim, K. Ramli, M. Salman, B. Pranggono, and E. R. Agustina, 'ARKAIV: Predicting Data Exfiltration Using Supervised Machine Learning Based on Tactics Mapping From Threat Reports and Event Logs,' IEEE Access, vol. 13, pp. 28381-28397, 2024. [13] C. G. Iroanwusi, F. E. Onuodu, D. I. Nelson, and B. A. Tom, 'Development of Cybercrime Prediction Model using Hybridized Algorithms,' International Journal of Computer Techniques–IJCT vol. 13, pp. 290-299, 2026. [14] X. Zhang, M. Wang, and J. Li, 'Convolutional neural network-based exfiltration detection for compressed and encrypted network traffic,' in IEEE Transactions on Information Forensics and Security, 2023, pp. 3421-3433. [15] X. Chen and A. Abidin, 'Coordinated data exfiltration detection using federated anomaly detection,' Journal of Cybersecurity Research, vol. 12, pp. 45-61, 2025.

More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY

Virtual Environments of Make Virtual Reality Applications Useful

Author: Ghaliya AlFarsi

Convolutional Neural Network-Based Detection of Facial Image Forgeries Using Binary Classification

Author: Ahmed Samaila1, Etemi. J. Garba2, and Oluborode Kayode O., Corresponding author

Transforming Mathematics Teacher Education Through Artificial Intelligence and Digital Innovation: Extent of Utilization, Challenges, and Strategies in Colleges of Education, Gombe State

Author: Yunusa, Samson PhD, Etuk Emmanuel Dan, Micah Michael, and Ismail Uzairu Usman

Certificate Authentication and Revocation System for IoT Devices using CoAP and CBOR Encoding in LoRaWAN

Author: Duke, Tamunotonye Juliana, Sako, D.J.S., Bennett, E.O.

Multiclass Chest X-Ray Classification Using Transfer Learning with Resnet50: Performance Evaluation Across Varying Train-Test Configurations

Author: Joshua Kolapo Awe,, Samson Afolabi Arekete, Olufade Falade Williams Onifade, Olufunmilayo Olopade,, Benjamin Segun Aribisala