@article{ART003353311},
author={Lee, Hyung Woo},
title={SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework},
journal={Journal of Internet of Things and Convergence},
issn={2466-0078},
year={2026},
volume={12},
number={3},
pages={10}
TY - JOUR
AU - Lee, Hyung Woo
TI - SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework
JO - Journal of Internet of Things and Convergence
PY - 2026
VL - 12
IS - 3
PB - The Korea Internet of Things Society
SP - 10
EP -
SN - 2466-0078
AB - With the increasing complexity of modern network environments and the diversification of security threats, the volume of logs generated by various security devices and services has grown rapidly, making the rapid and accurate identification of normal and abnormal behaviors a critical task in incident response and security monitoring. However, existing detection approaches have limitations in adequately capturing the diversity of log representations and the contextual differences of behaviors. To address this issue, this paper proposes SecuBERT, an improved BERT-based network log analysis system. The proposed framework defines profile sentences describing normal and abnormal behaviors, maps input logs into the BERT embedding space, and classifies events by measuring semantic similarity to the predefined profiles. In addition, keyword hint-based scoring and correction rules based on port and protocol characteristics are incorporated to improve the practicality and detection accuracy of the results. The proposed SecuBERT system demonstrated that effective network log-based anomaly detection is possible even in environments where large-scale labeled datasets are limited, and it also showed the potential to be extended into an AI-based automated detection system for real-world operational network log environments.
KW - BERT;Network Log;Anomaly Detection;AI based Detection;Visualization;Similarity
DO -
UR -
ER -
Lee, Hyung Woo. (2026). SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework. Journal of Internet of Things and Convergence, 12(3), 10.
Lee, Hyung Woo. 2026, "SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework", Journal of Internet of Things and Convergence, vol.12, no.3 10.
Lee, Hyung Woo "SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework" Journal of Internet of Things and Convergence 12.3 10 (2026) : 10.
Lee, Hyung Woo. SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework. 2026; 12(3), 10.
Lee, Hyung Woo. "SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework" Journal of Internet of Things and Convergence 12, no.3 (2026) : 10.
Lee, Hyung Woo. SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework. Journal of Internet of Things and Convergence, 12(3), 10.
Lee, Hyung Woo. SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework. Journal of Internet of Things and Convergence. 2026; 12(3) 10.
Lee, Hyung Woo. SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework. 2026; 12(3), 10.
Lee, Hyung Woo. "SecuBERT: AI-Based Network Anomaly Auto-Detection and Visualization Framework" Journal of Internet of Things and Convergence 12, no.3 (2026) : 10.
