National Cyber Defense: Analysis of Incident Severity Factors Using a Decision Tree

Cybersecurity became Indonesia’s national defense priority after the April 2024 ransomware attack on critical infrastructure exposed systemic vulnerabilities. Despite BSSN’s establishment, inter-agency coordination remains fragmented, and response delays persist. This study aims to identify the key determinants of cyber-incident severity and propose data-driven policy recommendations. A descriptive quantitative approach was applied to all 77 incidents recorded by BSSN from January to September 2024 a period chosen because it follows new regulatory measures introduced at the start of 2024 and includes multiple high-profile events. BSSN data were cross-referenced with Kominfo and Id-SIRTII logs (revealing an 8 percent discrepancy) to enhance validity. Preprocessing involved removing non-contributory fields, grouping by attack type, sector, and severity, converting categorical variables (Incident Type, Sector, Origin, Mitigation Measures, Response Time, Status) into factors, and stratified splitting into 80 percent training and 20 percent testing subsets. A decision tree model in RStudio (pruned with cp = 0.05) yielded 93.75 percent accuracy, validated by 10-fold cross-validation (mean accuracy 92.5 percent, SD 2.1 percent). Results show Incident Type as the strongest predictor of severity, followed by Mitigation Measures and Response Time. Attacks responded to within 24 hours seldom exceed medium severity, whereas delays over 48 hours, especially for exploits, Trojans, and malware, almost always result in critical outcomes. Additionally, incidents from the United States and Singapore disproportionately target underdeveloped infrastructure and governance sectors, increasing severity. To bolster Indonesia’s cybersecurity resilience, recommendations include: expanding secure, evenly distributed digital infrastructure; establishing and reinforcing provincial CSIRTs; enforcing uniform audit and certification standards; and integrating digital literacy into education. Ultimately, deepening ASEAN CERT integration through synchronized incident classification and real-time threat attribution will bridge national and regional defense gaps, thereby enhancing cross-border response capabilities

Authors

Institutions

Publication Details

Journal
Jurnal Pertahanan Media Informasi tentang Kajian dan Strategi Pertahanan yang Mengedepankan Identity Nasionalism dan Integrity
Published
2025-07-20
DOI
https://doi.org/10.33172/jp.v11i1.19798
Primary Topic
Information and Cyber Security
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

National Cyber Defense: Analysis of Incident Severity Factors Using a Decision Tree

Khaerul Umam, Reyhan Fakhreja, Kamila Zahra, Imat Siti Nurjiah
Jurnal Pertahanan Media Informasi tentang Kajian dan Strategi Pertahanan yang Mengedepankan Identity Nasionalism dan Integrity
Information and Cyber Security
article

National Cyber Defense: Analysis of Incident Severity Factors Using a Decision Tree

Khaerul Umam, Reyhan Fakhreja, Kamila Zahra, Imat Siti Nurjiah
article en

Abstract

Cybersecurity became Indonesia’s national defense priority after the April 2024 ransomware attack on critical infrastructure exposed systemic vulnerabilities. Despite BSSN’s establishment, inter-agency coordination remains fragmented, and response delays persist. This study aims to identify the key determinants of cyber-incident severity and propose data-driven policy recommendations. A descriptive quantitative approach was applied to all 77 incidents recorded by BSSN from January to September 2024 a period chosen because it follows new regulatory measures introduced at the start of 2024 and includes multiple high-profile events. BSSN data were cross-referenced with Kominfo and Id-SIRTII logs (revealing an 8 percent discrepancy) to enhance validity. Preprocessing involved removing non-contributory fields, grouping by attack type, sector, and severity, converting categorical variables (Incident Type, Sector, Origin, Mitigation Measures, Response Time, Status) into factors, and stratified splitting into 80 percent training and 20 percent testing subsets. A decision tree model in RStudio (pruned with cp = 0.05) yielded 93.75 percent accuracy, validated by 10-fold cross-validation (mean accuracy 92.5 percent, SD 2.1 percent). Results show Incident Type as the strongest predictor of severity, followed by Mitigation Measures and Response Time. Attacks responded to within 24 hours seldom exceed medium severity, whereas delays over 48 hours, especially for exploits, Trojans, and malware, almost always result in critical outcomes. Additionally, incidents from the United States and Singapore disproportionately target underdeveloped infrastructure and governance sectors, increasing severity. To bolster Indonesia’s cybersecurity resilience, recommendations include: expanding secure, evenly distributed digital infrastructure; establishing and reinforcing provincial CSIRTs; enforcing uniform audit and certification standards; and integrating digital literacy into education. Ultimately, deepening ASEAN CERT integration through synchronized incident classification and real-time threat attribution will bridge national and regional defense gaps, thereby enhancing cross-border response capabilities

Jurnal Pertahanan Media Informasi tentang Kajian dan Strategi Pertahanan yang Mengedepankan Identity Nasionalism dan IntegrityVol. 11(1)
Sunan Gunung Djati State Islamic University Bandung (ID)
Openalex Percentile: Top 60%
Information and Cyber Security
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.