This paper introduces a novel Concave Matrix Generative Adversarial Network (CM-GAN) designed for advanced cybersecurity threat detection and contextual awareness modeling in digital infrastructures. The proposed framework integrates a concave matrix regularization mechanism to embed non-linear structural dependencies between independent (attack, defense, response) and intervening (user behavior, network load, system vulnerability) variables within the GAN learning process. Unlike traditional GAN-based models, CM-GAN enhances interpretability, training stability, and detection precision. The model is evaluated using the CSE-CIC-IDS2018 dataset and benchmarked against two customized baselines: the Matrix GAN with Awareness (MGAN) and the Matrix-Based GAN (MB-GAN). CM-GAN demonstrates superior performance across binary and multiclass classification tasks, achieving accuracy, recall, and F1-scores exceeding 99%, and demonstrating higher anomaly realism with robust detection fidelity. These results confirm the efficacy of CM-GAN as a structure-aware, context-sensitive solution for real-time cyber-threat intelligence, particularly in resource-constrained environments such as academic networks.
| Published in | Machine Learning Research (Volume 10, Issue 1) |
| DOI | 10.11648/j.mlr.20251001.17 |
| Page(s) | 69-90 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
CM-GAN, Concave Matrix, Cybersecurity Awareness, Threat Detection, CSE-CIC-IDS2018
| [1] | Cybersecurity Ventures. (2022). 2022 cybersecurity almanac. Cybersecurity Ventures. |
| [2] | J. Internet World Stats. (2023). Usage and population statistics. Internet World Stats. |
| [3] | IBM Security. (2021). Cost of a data breach report. IBM Corporation. |
| [4] | Hassan, A., Hadullo, K., and Tole, K. (2025). Advances in cybersecurity: A literature review. International Journal of Computer Applications Technology and Research, 14(1), 112-115. |
| [5] | McAfee. (2021). The hidden costs of cybercrime. McAfee, LLC. |
| [6] | Accenture. (2020). State of cybersecurity report. Accenture PLC. |
| [7] | Kaspersky. (2021). IoT threat evolution. Kaspersky Lab. |
| [8] | Gartner. (2020). AI in security: Opportunities and risks. Gartner, Inc. |
| [9] | Cisco. (2021). Annual cybersecurity report. Cisco Systems. |
| [10] | African Union. (2021). Cybersecurity and the digital economy. African Union Commission. |
| [11] | ITU. (2022). Global cybersecurity index-Africa regional insights. International Telecommunication Union. |
| [12] | World Bank. (2020). Digital Africa: ICT and economic transformation. The World Bank Group. |
| [13] | Communications Authority of Kenya. (2022). Quarterly cybersecurity report. Government of Kenya. |
| [14] | Nigeria Communications Commission. (2021). Cyber incidents overview. Federal Republic of Nigeria. |
| [15] | South African Department of Communications. (2022). Cybersecurity and public sector. Republic of South Africa. |
| [16] | ENISA. (2021). Cybersecurity challenges in developing economies. European Union Agency for Cybersecurity. |
| [17] | Deloitte Africa. (2020). Africa cyber threat landscape. Deloitte & Touche. |
| [18] | Serianu. (2021). Africa cybersecurity report. Serianu Limited. |
| [19] | UNESCO. (2020). Cybersecurity in higher education. United Nations Educational, Scientific and Cultural Organization. |
| [20] | Juma, V., and Mburu, P. (2021). Cyber threats in African universities: A review. Journal of African Cyber Studies, 4(2): 45-59. |
| [21] | International Journal of Cyber Security and Digital Forensics. (2020). University network vulnerabilities. Int. J. Cyber Sec. Dig. For., 9(1): 33-50. |
| [22] | Beuran, R., Pham, C., Chinen, K., Tan, Y., and Shinoda, Y. (2020). Cybersecurity challenges in academia. IEEE Access, 8: 211025-211037. |
| [23] | Eken, S., and Yildirim, S. (2021). Cyber risk factors in academic networks. International Journal of Computer and Information Engineering, 15(8): 689-694. |
| [24] | Abok, A., and Wambua, M. (2021). Kenya’s university ICT risk posture. African Journal of Information Systems, 13(4): 152-165. |
| [25] | DTandiya, N., and Otieno, S. (2022). Cybersecurity policy gaps in higher education. East African ICT Journal, 5(1): 20-29. |
| [26] | Masinde, V. (2021). Cyber awareness and training in Kenyan universities. International Review of Cybersecurity Education, 7(2): 95-110. |
| [27] | Jansen, H., and Yusuf, M. (2022). Digital hygiene in learning institutions. Global Journal of Educational Technology, 14(3): 210-225. |
| [28] | ENISA. (2020). Awareness raising strategies for cybersecurity. ENISA Reports Series, 2020/11. |
| [29] | ISO/IEC. (2022). 27001 framework for security awareness. ISO/IEC Standards Organization. |
| [30] | NIST. (2021). Cybersecurity awareness and workforce training. National Institute of Standards and Technology. |
| [31] | Ponemon Institute. (2021). The role of awareness in reducing attacks. Ponemon Research. |
| [32] | Cyberaware.gov.uk. (2022). Cyber essentials and awareness. UK Government. |
| [33] | Bada, A., Sasse, A., and Nurse, J. (2020). The human factor in cybersecurity awareness. International Journal of Cyber Behavior, Psychology and Learning, 10(4): 12-24. |
| [34] | Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial networks. Advances in Neural Information Processing Systems, 27. |
| [35] | Mirsky, Y., Doitshman, T., Elovici, Y., and Shabtai, A. (2018). Kitsune: An ensemble of autoencoders for online network intrusion detection. Network and Distributed Systems Security Symposium (NDSS). |
| [36] | Kim, H., and Park, Y. (2021). AI-based threat detection with real-time analytics. Journal of Network Intelligence, 6(4): 800-812. |
| [37] | Lin, Y., and Chen, C. (2022). GAN-based cyber threat simulation and detection. Security and Communication Networks, 2022: Article ID 5678293. |
| [38] | Zhang, W., Zhang, Y., and Wang, S. (2021). Data-driven cybersecurity with GANs. IEEE Transactions on Information Forensics and Security, 16: 5120-5132. |
| [39] | Liu, Y., Wang, X., and Yang, H. (2020). Adversarial learning for intrusion detection. Computers & Security, 92: 101740. |
| [40] | Sun, X., and Meng, Y. (2022). Anomaly detection using GANs in network traffic. Applied Sciences, 12(1): 34-49. |
| [41] | Alom, M., Taha, T., Yakopcic, C., Westberg, S., and Asari, V. (2019). A survey on deep learning applications in cybersecurity. Journal of Big Data, 6: 1-30. |
| [42] | Yang, B., and Wu, J. (2022). Security-aware GANs for threat classification. IEEE Access, 10: 11453-11464. |
| [43] | Zhou, J., and Zhao, K. (2021). Matrix structures in AI-based cybersecurity. ACM Transactions on Privacy and Security, 24(3): 1-21. |
| [44] | Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional GANs. arXiv preprint arXiv:1511.06434. |
| [45] | Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein GAN. International Conference on Machine Learning (ICML). |
| [46] | Sharafaldin, I., Lashkari, A. H., and Ghorbani, A. A. (2018). Toward generating a new intrusion detection dataset and intrusion traffic characterization. ICISSP. |
| [47] | Sommer, R., and Paxson, V. (2010). Outside the closed world: On using machine learning for network intrusion detection. IEEE Symposium on Security and Privacy. |
| [48] | Yuan, X., He, P., Zhu, Q., and Li, X. (2019). Adversarial examples: Attacks and defenses for deep learning. IEEE Transactions on Neural Networks and Learning Systems, 30(9), 2805-2824. |
| [49] | Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784. |
| [50] | Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016). InfoGAN: Interpretable representation learning by information maximizing GANs. NeurIPS. |
| [51] | Moustafa, N., and Slay, J. (2015). UNSW-NB15: A comprehensive data set for network intrusion detection systems. Computers and Security. |
| [52] | Ring, M., Wunderlich, S., Scheuring, D., Landes, D., and Hotho, A. (2019). A survey of network- based intrusion detection data sets. Computers and Security. Mathematical Structures in Computer Science, 30(5): 621-640. |
| [53] | Kim, G., Lee, S., and Kim, S. (2014). A novel hybrid intrusion detection method integrating anomaly detection with misuse detection. Expert Systems with Applications. |
| [54] | Ahmed, M., Mahmood, A. N., and Hu, J. (2016). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19-31. |
| [55] | Xu, W., Qi, Y., and Evans, D. (2016). Automatically evading classifiers: A case study on PDF malware classifiers. Network and Distributed System Security Symposium (NDSS). |
| [56] | Qian, T., and Wang, Z. (2020). Concave matrix theory for security applications. Mathematical Structures in Computer Science, 30(5): 621-640. |
| [57] | Fang, L., and Hu, Y. (2022). Nonlinear optimization in cyber defense modeling. Cyber Systems and Optimization, 18(4): 455-469. |
| [58] | Li, M., and Gao, H. (2021). Concave matrix analysis in machine learning. Neural Computing and Applications, 33: 12345-12360. |
| [59] | Hassan, R., and Abdi, M. (2023). Optimizing threat response in constrained systems. Cyber Defense Analytics Journal, 8(1): 34-49. |
| [60] | Owino, P., and Ng’ang’a, S. (2024). Adaptive security models in university networks. Journal of Academic ICT Security, 9(2): 100-117. |
| [61] | Wekesa, C., and Musyoka, D. (2023). Challenges in academic cybersecurity. African Educational Cybersecurity Review, 12(1): 23-38. |
APA Style
Fondo, E., Mwakondo, F., Tole, K. (2025). A Concave Matrix Generative Adversarial Network Model for Detecting and Enhancing Cyber-Security Threats and Awareness. Machine Learning Research, 10(1), 69-90. https://doi.org/10.11648/j.mlr.20251001.17
ACS Style
Fondo, E.; Mwakondo, F.; Tole, K. A Concave Matrix Generative Adversarial Network Model for Detecting and Enhancing Cyber-Security Threats and Awareness. Mach. Learn. Res. 2025, 10(1), 69-90. doi: 10.11648/j.mlr.20251001.17
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.mlr.20251001.17,
author = {Edward Fondo and Fullgence Mwakondo and Kevin Tole},
title = {A Concave Matrix Generative Adversarial Network Model for Detecting and Enhancing Cyber-Security Threats and Awareness
},
journal = {Machine Learning Research},
volume = {10},
number = {1},
pages = {69-90},
doi = {10.11648/j.mlr.20251001.17},
url = {https://doi.org/10.11648/j.mlr.20251001.17},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mlr.20251001.17},
abstract = {This paper introduces a novel Concave Matrix Generative Adversarial Network (CM-GAN) designed for advanced cybersecurity threat detection and contextual awareness modeling in digital infrastructures. The proposed framework integrates a concave matrix regularization mechanism to embed non-linear structural dependencies between independent (attack, defense, response) and intervening (user behavior, network load, system vulnerability) variables within the GAN learning process. Unlike traditional GAN-based models, CM-GAN enhances interpretability, training stability, and detection precision. The model is evaluated using the CSE-CIC-IDS2018 dataset and benchmarked against two customized baselines: the Matrix GAN with Awareness (MGAN) and the Matrix-Based GAN (MB-GAN). CM-GAN demonstrates superior performance across binary and multiclass classification tasks, achieving accuracy, recall, and F1-scores exceeding 99%, and demonstrating higher anomaly realism with robust detection fidelity. These results confirm the efficacy of CM-GAN as a structure-aware, context-sensitive solution for real-time cyber-threat intelligence, particularly in resource-constrained environments such as academic networks.
},
year = {2025}
}
TY - JOUR T1 - A Concave Matrix Generative Adversarial Network Model for Detecting and Enhancing Cyber-Security Threats and Awareness AU - Edward Fondo AU - Fullgence Mwakondo AU - Kevin Tole Y1 - 2025/06/30 PY - 2025 N1 - https://doi.org/10.11648/j.mlr.20251001.17 DO - 10.11648/j.mlr.20251001.17 T2 - Machine Learning Research JF - Machine Learning Research JO - Machine Learning Research SP - 69 EP - 90 PB - Science Publishing Group SN - 2637-5680 UR - https://doi.org/10.11648/j.mlr.20251001.17 AB - This paper introduces a novel Concave Matrix Generative Adversarial Network (CM-GAN) designed for advanced cybersecurity threat detection and contextual awareness modeling in digital infrastructures. The proposed framework integrates a concave matrix regularization mechanism to embed non-linear structural dependencies between independent (attack, defense, response) and intervening (user behavior, network load, system vulnerability) variables within the GAN learning process. Unlike traditional GAN-based models, CM-GAN enhances interpretability, training stability, and detection precision. The model is evaluated using the CSE-CIC-IDS2018 dataset and benchmarked against two customized baselines: the Matrix GAN with Awareness (MGAN) and the Matrix-Based GAN (MB-GAN). CM-GAN demonstrates superior performance across binary and multiclass classification tasks, achieving accuracy, recall, and F1-scores exceeding 99%, and demonstrating higher anomaly realism with robust detection fidelity. These results confirm the efficacy of CM-GAN as a structure-aware, context-sensitive solution for real-time cyber-threat intelligence, particularly in resource-constrained environments such as academic networks. VL - 10 IS - 1 ER -
Computer Science and Information Technology, Institute of Computing and Informatics, Technical University of Mombasa, Mombasa, Kenya
Computer Science and Information Technology, Institute of Computing and Informatics, Technical University of Mombasa, Mombasa, Kenya
Computer Science and Information Technology, Institute of Computing and Informatics, Technical University of Mombasa, Mombasa, Kenya
