Effective Classification and Intrusion Detection with Improved Optimization Techniques and a Deep MLP Model

P. Kiruthiga C. Sathish Kumar D. Chitra K. Rizwana Parveen P. Thangaraju S. Prathi S. Silvia Priscila Effective Classification and Intrusion Detection with Improved Optimization Techniques and a Deep MLP Model Abstract

This paper extends our previous work by presenting the Enhanced Multi Layer Perceptron(MLP) model as a method for intrusion detection and classification, as we seek to combat a growing challenge of securing networks against emerging cyber threats. Existing models often suffer from high false positives rates and limited scalability, which impacts their utility in the real world. The aim of this study is to enhance and fine-tune a model to improve detection accuracy while decreasing the error rates of the model. The Enhanced MLP was evaluated through extensive experimentation using a real-world dataset in order to allow for an evaluation of many different categories of attacks and network behavior anomalies. Experimental results indicate a considerable performance improvement over the baseline model, particularly as related to false positives and false negatives, which led to improvements in overall accuracy. Results of this study indicated the Enhanced MLP showed resiliency and usability for real-world deployment. In summary, we conclude the Enhanced MLP improves automated threat detection and can provide insight into the future development of next generation intrusion detection systems (IDS).
Chapter 3 2026 03 03 2026 35 46 1 10.1007/springer_crossmark_policy link.springer.com false 3 March 2026 AI-FCDAC International Workshop on AI & ML - Frontiers in Cross Disciplinary Applications & Case Studies Rajkot India 2025 11 September 2025 11 September 2025 1 ai-fcdac2025 https://ascisworkshop.org/ 10.1007/978-3-032-17300-3_3 https://link.springer.com/10.1007/978-3-032-17300-3_3 https://link.springer.com/content/pdf/10.1007/978-3-032-17300-3_3 Comput. Secur. P Garcia-Teodoro 28 1-2 18 2009 10.1016/j.cose.2008.08.003 Garcia-Teodoro, P., Diaz-Verdejo, J., Maciá-Fernández, G., Vázquez, E.: Anomaly-based network intrusion detection: Techniques, systems and challenges. Comput. Secur. 28(1-2), 18–28 (2009) J. Netw. Comput. Appl. R Singh 123 1 2018 Singh, R., et al.: Zero-day attack detection: A survey. J. Netw. Comput. Appl. 123, 1–13 (2018) 10.1109/SP.2010.25 Sommer, R., Paxson, V.: Outside the closed world: On using machine learning for network intrusion detection. 2010 IEEE Symposium on Security and Privacy. IEEE. 2010. IEEE Commun. Surv. Tutor. AL Buczak 18 2 1153 2016 10.1109/COMST.2015.2494502 Buczak, A.L., Guven, E.: A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Commun. Surv. Tutor. 18(2), 1153–1176 (2016) J. Netw. Comput. Appl. G Wang 127 1 2019 10.1016/j.jnca.2018.11.003 Wang, G., et al.: A survey on feature engineering for network intrusion detection. J. Netw. Comput. Appl. 127, 1–14 (2019) J. Netw. Comput. Appl. C Yin 143 1 2020 Yin, C., Zhu, Y., Fei, J., He, X.: Deep learning for intrusion detection: A survey. J. Netw. Comput. Appl. 143, 1–15 (2020) J. Netw. Comput. Appl. Y Li 135 1 2019 Li, Y., et al.: Deep learning for network intrusion detection: A review. J. Netw. Comput. Appl. 135, 1–13 (2019) IEEE Trans. Neural Netw. Learn. Syst. N Gao 30 11 3311 2019 Gao, N., et al.: Labeled data generation for network intrusion detection using generative adversarial networks. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3311–3322 (2019) IEEE Trans. Ind. Inf. J Zhang 15 4 1733 2019 Zhang, J., et al.: Distributed deep learning for network intrusion detection. IEEE Trans. Ind. Inf. 15(4), 1733–1742 (2019) IEEE Trans. Dependable Secure Comput. N Gao 17 4 761 2020 Gao, N., et al.: Generative adversarial networks for network intrusion detection. IEEE Trans. Dependable Secure Comput. 17(4), 761–774 (2020) J. Parallel Distrib. Comput. Y Zhang 143 102 2020 10.1016/j.jpdc.2020.04.004 Zhang, Y., et al.: Distributed deep learning-based intrusion detection system for cloud computing. J. Parallel Distrib. Comput. 143, 102–113 (2020) Appl. Intell. Z Geng 55 141 2025 10.1007/s10489-024-05872-6 Geng, Z., Li, X., Ma, B., Han, Y.: Improved convolution neural network integrating attention based deep sparse auto encoder for network intrusion detection. Appl. Intell. 55, 141 (2025). https://doi.org/10.1007/s10489-024-05872-6 Syst. Soft Comput. MKU Ahamed 7 2025 10.1016/j.sasc.2024.200182 Ahamed, M.K.U., Karim, A.: Cascaded intrusion detection system using machine learning. Syst. Soft Comput. 7, 200182 (2025). https://doi.org/10.1016/j.sasc.2024.200182 Decis. Making Adv. HB Ul Haq 3 1 126 2025 10.31181/dma31202559 Ul Haq, H.B., Younis, R., Ali, M.S.: Towards robust network security: Evaluating machine learning algorithms for intrusion detection. Decis. Making Adv. 3(1), 126–138 (2025). https://doi.org/10.31181/dma31202559 J. Supercomput. L Shi 81 110 2025 10.1007/s11227-024-06475-1 Shi, L., Yang, Q., Gao, L., Ge, H.: An ensemble system for machine learning IoT intrusion detection based on enhanced artificial hummingbird algorithm. J. Supercomput. 81, 110 (2025). https://doi.org/10.1007/s11227-024-06475-1 Decis. Making Adv. S Saravanan 3 1 96 2025 10.31181/dma31202556 Saravanan, S., Dar, S.A., Rather, A.A., Qayoom, D., Ali, I.: Deep learning models for intrusion detection systems in MANETs: A comparative analysis. Decis. Making Adv. 3(1), 96–110 (2025). https://doi.org/10.31181/dma31202556 J Han 2001 Data Mining: Concepts and Techniques Han, J., Kamber, M.: Data Mining: Concepts and Techniques. Morgan Kaufmann. University of Illinois at Urbana-Champaign (2001) www.cs.uiuc.edu/~hanj Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. ISBN 978-0-387-31073-2 (Hardcover), ISBN 978-1-4939-3843-8 (Softcover).