Cybersecurity threat detection based on a UEBA framework using deep autoencoders
Published in AIMS Mathematics, 2025
Recommended citation: Fuentes, J., Ortega-Fernandez, I., Villanueva, N. M., & Sestelo, M. (2025). Cybersecurity threat detection based on a UEBA framework using deep autoencoders. AIMS Mathematics, 10(10), 23496–23517. https://doi.org/10.3934/math.20251043 https://doi.org/10.3934/math.20251043
User and Entity Behavior Analytics (UEBA) has emerged as a promising approach for detecting advanced cybersecurity threats by modeling behavioral patterns of users and systems. This paper presents a cybersecurity threat-detection framework based on deep autoencoders integrated within a UEBA architecture for anomaly detection in enterprise environments.
The proposed framework analyzes behavioral patterns extracted from security events and system logs to identify suspicious or anomalous activities. Deep autoencoders are employed to learn latent representations of normal behavior and detect deviations associated with cyber threats. The methodology enables scalable and adaptive threat detection while reducing dependence on manually defined rules and signatures.
Experimental results demonstrate the effectiveness of the proposed approach for identifying anomalous behaviors in cybersecurity scenarios, highlighting the potential of deep-learning-based UEBA systems for next-generation Security Operations Centers (SOC).