A Novel Web-Based Attack Detection Framework Using Geometric Algebra Bayesian Normalized Neural Network

Paper ID: EIJTEM_2018_5_4_31-37

Author's Name: Dileep Kumar Ghattamaneni

Volume: 5

Issue: 4

Year: 2018

Page No: 31-37

Abstract:

Web applications face an increasing number of sophisticated cyber threats, making efficient and accurate web attack detection a critical challenge. Traditional detection systems often suffer from high false positive rates and fail to adapt to evolving attack patterns. To address this, a novel detection model named DSN-EPO is proposed, combining Dynamic Slimmable Networks (DSN) with the Emperor Penguin Optimizer (EPO) to enhance detection precision and reduce computational complexity. The methodology involves preprocessing using Min-Max Scaler Normalization, feature selection via the biologically-inspired Mud Ring Algorithm, and feature extraction using Geometric Algebra Transformers to handle high-dimensional data. The DSN dynamically adjusts its structure based on input characteristics, while EPO efficiently optimizes the model’s parameters. Evaluation on the CSIC2010v2 dataset demonstrates the superiority of the DSN-EPO approach, achieving 96.8% accuracy, 96.2% precision, 95.6% recall, and a 95.9% F1-score, and outperforming conventional models such as HOODLE, A3C-BC, and ML-RL. Furthermore, DSN-EPO achieves the lowest detection time (32 ms) and computational cost, making it highly efficient for real-time implementation. In conclusion, the proposed DSN-EPO model provides a robust, adaptive, and computationally efficient solution for web attack detection, ensuring improved security against emerging threats in dynamic online environments.

Keywords: Emperor Penguin Optimizer, Geometric Algebra Transformers, Min-Max Scaler Normalization, Mud Ring Algorithm, Web attack detection.

References:

1. Jin, X., Cui, B., Yang, J. and Cheng, Z., 2018. Payload-based web attack detection using deep neural network.
In Advances on Broad-Band Wireless Computing, Communication and Applications: Proceedings of the 12th
International Conference on Broad-Band Wireless Computing, Communication and Applications (BWCCA-2017) (pp. 482-
488). Springer International Publishing.
2. Wankhede, S. and Kshirsagar, D., 2018, August. DoS attack detection using machine learning and neural network.
In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA) (pp. 1-5).
IEEE.
3. Zhang, M., Xu, B., Bai, S., Lu, S. and Lin, Z., 2017. A deep learning method to detect web attacks using a specially
designed CNN. In Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China,
November 14–18, 2017, Proceedings, Part V 24 (pp. 828-836). Springer International Publishing.
4. Wilson, D., Tang, Y., Yan, J. and Lu, Z., 2018, August. Deep learning-aided cyber-attack detection in power
transmission systems. In 2018 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1-5). IEEE.
5. Vartouni, A.M., Kashi, S.S. and Teshnehlab, M., 2018, February. An anomaly detection method to detect web attacks
using stacked auto-encoder. In 2018 6th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS) (pp. 131-134).
IEEE.
6. Zhang, M., Xu, B., Bai, S., Lu, S. and Lin, Z., 2017. A deep learning method to detect web attacks using a specially
designed CNN. In Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China,
November 14–18, 2017, Proceedings, Part V 24 (pp. 828-836). Springer International Publishing.
7. Dong, Y. and Zhang, Y., 2017. Adaptively detecting malicious queries in web attacks. arXiv preprint arXiv:1701.07774.
8. Wang, J., Zhou, Z. and Chen, J., 2018, February. Evaluating CNN and LSTM for web attack detection. In Proceedings of
the 2018 10th International Conference on Machine Learning and Computing (pp. 283-287).
9. Cao, X.H., Stojkovic, I. and Obradovic, Z., 2016. A robust data scaling algorithm to improve classification accuracies in
biomedical data. BMC bioinformatics, 17, pp.1-10..
10. Burke, B.J., 2018. Multi-Objective Optimisation of an Integrated Sugar Mill for Economic Enhancement.
11. Arsenovic, A., 2017. Applications of conformal geometric algebra to transmission line theory. IEEE Access, 5, pp.19920-
19941.
12. Yu, J., Yang, L., Xu, N., Yang, J. and Huang, T., 2018. Slimmable neural networks. arXiv preprint arXiv:1812.08928.
13. Dhiman, G. and Kumar, V., 2018. Emperor penguin optimizer: a bio-inspired algorithm for engineering
problems. Knowledge-Based Systems, 159, pp.20-50.

View PDF