A Framework for Proactive Cybersecurity Risk Management In Organizations Using K-Means Clustering Algorithm

Recent increase in the trends of threat frequency and evolution, Cyber Security risk management has now become the leading point of focus for most modern organizations. The use of reactive cyber security will always make a way to detect a new evolved threats later due to no predefinition. Anomaly detection on network-based attacks through behavioural traffic is considered the approach that organizations could implement for an immediate early identification to deal with these issues proactively. In this study, a framework was proposed to define a proactive cyber security risk management, using K-Means algorithm on behavioural network traffic analysis in order to detect network attack and classify traffic patterns into predefined classes. Multiple features from the traffic were extracted from IP, ARP, ICMP, and HTTP protocols that represented network communication patterns of the traffic. Cleaning, Feature selection, normalization, and preparation techniques were used during pre-processing of the data to optimize the clusters result. OOADM was used to design the frame work while the whole system was implemented in Python to cluster network traffic into “normal, MITM, DDoS and ransomware. The final experiment results on network traffic resulted in accuracy (98.47%), precision (95.8%), recall (96.4%), F1-Score (96.1%) and Detection Time (0.92s) respectively. The resulted confusion matrix indicates that minimal cases were misclassified and clear separation between “normal” and attack cases found. The proposed framework required moderate resources and minimized the labelling problem that makes it useful for large scaled real time monitoring and can be practically used for intrusion detection. Hence, this framework proved to be effective when compared to other models for network anomaly and will empower the organization’s IT managers to mitigate business data breaches, also it can enhance and upgrade the overall cybersecurity status.

Authors

Institutions

Publication Details

Journal
INTERNATIONAL JOURNAL OF MATHEMATICS AND COMPUTER RESEARCH
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24334722
Primary Topic
Network Security and Intrusion Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Framework for Proactive Cybersecurity Risk Management In Organizations Using K-Means Clustering Algorithm

Nlerum Promise Anebo, Kingsley Theophilus Igulu, Amaefula Ezienyi Modline
INTERNATIONAL JOURNAL OF MATHEMATICS AND COMPUTER RESEARCH
Network Security and Intrusion Detection
article

A Framework for Proactive Cybersecurity Risk Management In Organizations Using K-Means Clustering Algorithm

Nlerum Promise Anebo, Kingsley Theophilus Igulu, Amaefula Ezienyi Modline
article en

Abstract

Recent increase in the trends of threat frequency and evolution, Cyber Security risk management has now become the leading point of focus for most modern organizations. The use of reactive cyber security will always make a way to detect a new evolved threats later due to no predefinition. Anomaly detection on network-based attacks through behavioural traffic is considered the approach that organizations could implement for an immediate early identification to deal with these issues proactively. In this study, a framework was proposed to define a proactive cyber security risk management, using K-Means algorithm on behavioural network traffic analysis in order to detect network attack and classify traffic patterns into predefined classes. Multiple features from the traffic were extracted from IP, ARP, ICMP, and HTTP protocols that represented network communication patterns of the traffic. Cleaning, Feature selection, normalization, and preparation techniques were used during pre-processing of the data to optimize the clusters result. OOADM was used to design the frame work while the whole system was implemented in Python to cluster network traffic into “normal, MITM, DDoS and ransomware. The final experiment results on network traffic resulted in accuracy (98.47%), precision (95.8%), recall (96.4%), F1-Score (96.1%) and Detection Time (0.92s) respectively. The resulted confusion matrix indicates that minimal cases were misclassified and clear separation between “normal” and attack cases found. The proposed framework required moderate resources and minimized the labelling problem that makes it useful for large scaled real time monitoring and can be practically used for intrusion detection. Hence, this framework proved to be effective when compared to other models for network anomaly and will empower the organization’s IT managers to mitigate business data breaches, also it can enhance and upgrade the overall cybersecurity status.

INTERNATIONAL JOURNAL OF MATHEMATICS AND COMPUTER RESEARCH
Federal University Otuoke (NG), Ignatius Ajuru University of Education (NG)
Network Security and Intrusion Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon