The escalating complexity of legacy software systems and their susceptibility to cyber threats necessitate advanced approaches for modularization and security enhancement. This research investigates the integration of machine learning techniques to facilitate service boundary detection within legacy systems while simultaneously enhancing resilience against network intrusions. By synthesizing prior work in software modularization, anomaly detection, and artificial intelligence-driven security protocols, the study develops a comprehensive framework that combines algorithmic boundary delineation, clustering, and predictive anomaly detection. Emphasis is placed on the operationalization of machine learning-assisted service boundary identification, adaptive clustering methods, and ensemble-based anomaly classifiers. The study critically examines the efficacy of Hidden Markov Models (HMM), nearest neighbor algorithms, fuzzy association rules, and ensemble classifiers in both modularization and intrusion detection contexts. Empirical interpretations draw on prior implementations, highlighting improvements in system maintainability, reduced coupling, and enhanced detection rates of complex cyber threats. The framework addresses common challenges in integrating AI within legacy systems, including the heterogeneity of software components, data sparsity, and the evolving nature of network attacks. Limitations, such as model generalizability across heterogeneous systems and the interpretability of AI-driven modularization decisions, are discussed. Finally, the study articulates future research directions, proposing the convergence of explainable AI, dynamic service decomposition, and adaptive cybersecurity mechanisms to establish robust, high-performing, and secure legacy systems capable of meeting contemporary operational demands (Hebbar, 2022; Lin & Tsai, 2015; Khraisat et al., 2018).

Machine learning, service boundary detection, legacy systems, anomaly detection

S. S. Roy, D. Mittal, A. Basu, A. Abraham - Stock Market Forecasting Using LASSO Linear Regression Model. In AfroEuropean Conference for Industrial Advancement, pp. 371-381. Springer International Publishing, 2015.

Khraisat A, Gondal I, Vamplew P (2018) An anomaly intrusion detection system using C5 decision tree classifier. In: Trends and applications in knowledge discovery and data mining. Springer International Publishing, Cham, pp 149–155

S. S. Roy, V. M. Viswanatham - Classifying Spam Emails Using Artificial Intelligent Techniques. In International Journal of Engineering Research in Africa, vol. 22, pp. 152-161. Trans Tech Publications, 2016.

Hebbar, K. S. (2022). Machine learning-assisted service boundary detection for modularizing legacy systems. International Journal of Applied Engineering & Technology, 4(2), 401–414.

W. Hu, W. Hu, and S. Maybank, “AdaBoost-Based Algorithm for Network Intrusion Detection,” Trans. Sys. Man Cyber. Part B, vol. 38, no. 2, pp. 577-583, 2008.

Annachhatre, T. H. Austin, and M. Stamp, "Hidden Markov models for malware classification," Journal of Computer Virology and Hacking Techniques, vol. 11, no. 2, pp. 59–73, 2015/05/01 2015

S. Suthaharan - An iterative ellipsoid-based anomaly detection technique for intrusion detection systems, In Southeast on, Proceedings of IEEE, pp. 1-6, 2012.

C. F. Tsai and C. Y. Lin, “A Triangle Area Based Nearest Neighbors Approach to Intrusion Detection,” Pattern Recognition, vol. 43, pp. 222-229, 2013.

Lin, S.-W. Ke, and C.-F. Tsai, "CANN: an intrusion detection system based on combining cluster centers and nearest neighbors," Knowl-Based Syst, vol. 78, no. Supplement C, pp. 13–21, 2015/04/01/ 2015

Khraisat et al. Cybersecurity (2019) 2:20 https://doi.org/10.1186/s42400-019-0038-7

S. Elhag, A. Fernández, A. Bawakid, S. Alshomrani, and F. Herrera, "On the combination of genetic fuzzy systems and pairwise learning for improving detection rates on intrusion detection systems," Expert Syst Appl, vol. 42, no. 1, pp. 193–202, 2015

Tajbakhsh, M. Rahmati, and A. Mirzaei, “Intrusion detection using fuzzy association rules,” Applied Soft Computing, vol. 9, no. 2, pp. 462-469, 200

9

G. Thatte, U. Mitra, and J. Heidemann, “Parametric Methods for Anomaly Detection in Aggregate Traffic,” Networking, IEEE/ACM Transactions on, vol. 19, no. 2, pp. 512-525, 2011

Yu, H. Kai, and K. Wei-Shinn, “Collaborative Detection of DDoS Attacks over Multiple Network Domains,” Parallel and Distributed Systems, IEEE Transactions on, vol. 18, pp. 1649–1662, 2007

Kshetri N, VoasJ (2017) Hacking power grids: a current problem. Computer50(12):91–95

Khraisat A, Gondal I, Vamplew P (2018) An anomaly intrusion detection system using C5 decision tree classifier. In: Trends and applications in knowledge discovery and data mining. Springer International Publishing, Cham, pp 149–155