AN EXPLAINABLE MACHINE LEARNING FRAMEWORK FOR CYBERSECURITY AND DIGITAL SELF GOVERNANCE IN LOCAL GOVERNMENT NETWORKS
Lex localis - Journal of Local Self-Government · 01.09.2026 · 313-326
DOI: 10.52152/zsc9dh53 ↗Kurz gefasst
Fachartikel in der Zeitschrift Lex localis - Journal of Local Self-Government, online erschienen am 01.09.2026. Verfasst von R Kalaivani und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Local governments increasingly depend on connected service platforms, networked sensors, digital records, and inter-organizational data exchange. These systems create an operational need for intrusion detection that is accurate, explainable, privacy-conscious, and compatible with the accountability obligations of local self-government. This article proposes a governance-aware machine-learning framework that combines local network monitoring, privacy-aware preprocessing, lightweight supervised detection, explainable alerts, and federated model improvement. The technical core specifies data preparation, class-imbalance handling, model training, risk scoring, and evaluation through six formal expressions. A governance control plane links model outputs to human verification, role-based access, retention rules, audit logs, and incident-response responsibilities. The design is intended for municipal networks with heterogeneous technical capacity and limited ability to centralise sensitive traffic data. A reproducible evaluation protocol is defined around public intrusion-detection benchmarks, time-aware train-validation-test separation, and accuracy, precision, recall, F1-score, false-positive rate, latency, and communication cost. To demonstrate how the proposed evaluation should be reported, the manuscript includes an explicitly illustrative numerical scenario; these values are not empirical findings and must be replaced by results from executed experiments before submission. The contribution is therefore a testable engineering architecture coupled with a local-governance implementation model, rather than a claim that a deployed municipal system has already been validated.
Zitieren
APA
Kalaivani, R., & V.Vennila, D. (2026). AN EXPLAINABLE MACHINE LEARNING FRAMEWORK FOR CYBERSECURITY AND DIGITAL SELF GOVERNANCE IN LOCAL GOVERNMENT NETWORKS. Lex localis - Journal of Local Self-Government, 313-326. https://doi.org/10.52152/zsc9dh53
Vancouver
Kalaivani R, V.Vennila D. AN EXPLAINABLE MACHINE LEARNING FRAMEWORK FOR CYBERSECURITY AND DIGITAL SELF GOVERNANCE IN LOCAL GOVERNMENT NETWORKS. Lex localis - Journal of Local Self-Government. 2026:313-326. doi:10.52152/zsc9dh53
BibTeX
@article{Kalaivani2026,
author = {Kalaivani, R and V.Vennila, Dr.},
title = {AN EXPLAINABLE MACHINE LEARNING FRAMEWORK FOR CYBERSECURITY AND DIGITAL SELF GOVERNANCE IN LOCAL GOVERNMENT NETWORKS},
journal = {Lex localis - Journal of Local Self-Government},
year = {2026},
pages = {313--326},
doi = {10.52152/zsc9dh53}
}
EUVIMED