An Enhanced Model for Server-Side Attack Detection and Blocking in Cloud Computing Environment

Akanwa A. O; Matthias D; Nwiabu N. D; Taylor O. E

doi:10.56201/ijcsmt.vol.12.no6.2026.pg111.125

📄 Download Paper

An Enhanced Model for Server-Side Attack Detection and Blocking in Cloud Computing Environment

Akanwa A. O, Matthias D, Nwiabu N. D, Taylor O. E

Abstract

The rapid expansion of cloud computing has revolutionized IT infrastructure, offering significant benefits in scalability, flexibility, and cost-efficiency. However, its growth has introduced critical security challenges, particularly in the form of server-side attacks that exploit the dynamic and multi-tenant architecture of cloud environments. Currently, existing systems are faced with several limitations, including the difficulty in detecting and blocking server-side attacks in real time, challenges in accurately classifying evolving attack vectors, and the inability to ensure robust data isolation and privacy within shared infrastructures. This study developed an adaptive server-side attack detection and blocking system suitable for cloud computing environments. The developed system integrates a Neuro-Fuzzy Inference System for intelligent detection and blocking and employs Support Vector Machine for classifying sophisticated and previously unseen attack traffic patterns. To uphold data isolation and enhance privacy and security, the system incorporates the Cheon-Kim-Kim-Song scheme of Homomorphic Encryption (HE), ensuring that sensitive information (both in transit and at rest) remains secure. Furthermore, an Object-Oriented Design Approach was adopted for the designing and modelling of the system’s components. The implementation of the system was achieved using Visual Basic (VB) .Net 2022 for system interactive interface designing and coding with plugged-in Python programming language libraries for Machine Learning (ML) task. The system utilized the Microsoft Structured Query Language management studio as its database server. Seven network-based traffic features were selected as input variables to the developed system. These features are the Timestamp, Source IP, Destination IP, Source Port, Destination Port, Protocol, and Payload data. The developed system was trained using Backpropagation method, while the testing and performance evaluation was achieved using the Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CICIDS2017) benchmark dataset. The developed system achieved a 99% accuracy rate in detection, a precision of 99.5%, recall of 99.5%, and an F1-score of 99.5%. In terms of performance in blocking malicious network traffic patterns, it recorded a True Negative Rate of 99.5% and a remarkably low False Positive Rate of 0.05%. Further, in privacy preservation, the encryption and decryption processes demonstrated average execution times of 112ms and 89ms, respectively, with a ciphertext expansion ratio of 1.5×, enabling secure processing without compromising performance. These results affirm that the developed system provides a robust, adaptive, and privacy-preserving solution for mitigating a broad spectrum of server-side attacks in cloud settings.

Keywords

Server-Side AttackCloud SecurityNeuro-Fuzzy SystemsSupport Vector MachineIJCSMT Homomorphic EncryptionPrivacy Preservation

References

[1] O. D. Segun-Falade, O. S. Osundare, W. E. Kedi, P. A. Okeleke, T. I. Ijomah, and O. Y. Abdul-Azeez, 'Assessing the transformative impact of cloud computing on software deployment and management,' Computer Science & IT Research Journal, vol. 5, p. 2024, 2024. [2] N. K. A. Nemirajaiah and C. K. Raju, 'An Insight Into Security Issues Prevailing In The Cloudified Era,' in 2024 1st International Conference on Advances in Computing, Communication and Networking (ICAC2N), 2024, pp. 310-319. [3] Y. Jung, J. Lee, M. Kim, and S. Lee, 'Systematic Analysis of Integrity Threats and Defense Strategies in the Metaverse,' KSII Transactions on Internet & Information Systems, vol. 19, 2025. [4] S. Kumar, S. J. Serrao, G. N. Sumanth, and K. Raghunandan, 'Web and Server Attacks: Research and Analysis,' in Self-Powered AIoT Systems, ed: Apple Academic Press, 2025, pp. 295-314. [5] I. Davies, O. Taylor, V. Anireh, and E. Bennett, 'A Distributed Intrusion Detection System for IoT-Enabled Network and Devices using Hybrid Technique,' International Journal of Computer Science and Mathematical Theory , vol. 10, pp. 141-156, 2024. [6] A. Elgasaier, S. O. Sati, and M. Mansour, 'Comprehensive DDoS Detection Framework for Cloud Service Providers,' in 2026 IEEE 5th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), 2026, pp. 454-459. [7] O. E. Taylor and I. N. Davies, 'A Model for Enhancing Security and Privacy in Pervasive Computing using Homomorphic Encryption ' International Journal of Computer Sciences and Engineering, vol. 13, pp. 21-29, 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. Jabiyev, O. Mirzaei, A. Kharraz, and E. Kirda, 'Preventing server-side request forgery attacks,' in Proceedings of the 36th Annual ACM Symposium on Applied Computing, 2021, pp. 1626-1635. [10] S. Sekar, P. R. Parvathy, G. K. Gupta, T. Rajagopalan, C. C. S. C. B. Basavaraddi, K. Padmanaban, et al., 'Intrusion detection and prevention using Bayesian decision with fuzzy logic system,' International Journal of Electrical and Computer Engineering , vol. 15, pp. 1200-1208, 2025. [11] S. A. Ahmed, E. H. Khalifa, M. Nawaz, F. A. Abdalla, and A. F. Mahmoud, 'Enhancing Cloud Data Center Security through Deep Learning: A Comparative Analysis of RNN, CNN, and LSTM Models for Anomaly and Intrusion Detection,' Engineering, Technology & Applied Science Research, vol. 15, pp. 20071-20076, 2025. [12] J. R. Tadhani, V. Vekariya, V. Sorathiya, S. Alshathri, and W. El-Shafai, 'Securing web applications against XSS and SQLi attacks using a novel deep learning approach,' Scientific Reports, vol. 14, p. 1803, 2024. [13] F. Schmid, S. Mukherjee, S. Picek, M. Stöttinger, F. De Santis, and C. Rechberger, 'Towards private deep learning-based side-channel analysis using homomorphic encryption: Opportunities and limitations,' in International Workshop on Constructive IJCSMT Side-Channel Analysis and Secure Design, 2024, pp. 133-154. [14] Y. Deng, B. Guo, and S. Chen, 'Privacy-Preserving Approach to Edge Federated Learning Based on Blockchain and Fully Homomorphic Encryption,' Electronics, vol. 14, p. 361, 2025. [15] M. Dib and S. Pierre, 'HSM-Based Architecture to Detect Insider Attacks on Server-Side Data,' IEEE Transactions on Information Forensics and Security, 2025. [16] B. Konda, M. Yenugula, V. K. Kasula, and A. R. Yadulla, 'A Public Key Searchable Encryption Scheme Based on Blockchain Using Random Forest Method,' International Journal Of Research In Electronics And Computer Engineering, vol. 12, pp. 77-83, 2024.

An Enhanced Model for Server-Side Attack Detection and Blocking in Cloud Computing Environment

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY