Identification of Zero-Day Threats in Enterprise Environments Using Deep Learning Models.
DOI:
https://doi.org/10.5281/zenodo.15149234Keywords:
anomaly detection, artificial intelligence, cybersecurity, deep learning, network traffic, neural networks, zero-day threatsAbstract
In today’s cybersecurity landscape, zero-day threats pose one of the most critical challenges due to their unpredictable nature and the lack of predefined patterns for early detection. This article addresses this issue by presenting the design and implementation of a deep learning-based system that combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to identify such threats within enterprise network traffic. Using both real and simulated datasets, the model achieved an accuracy of 96.84%, significantly outperforming traditional signature-based approaches. These results highlight the system’s adaptability and effectiveness in countering emerging threats, underscoring the importance of integrating advanced artificial intelligence technologies into enterprise cybersecurity to safeguard digital assets and ensure operational continuity.
References
Cruz, A., & Núñez, S. (2021). Redes neuronales ligeras para la optimización de sistemas de seguridad. Revista de Matemáticas Aplicadas a la Ciberseguridad, 4(2), 98-115.
Cruz, J., & Pineda, G. (2021). Detección de amenazas cibernéticas mediante aprendizaje profundo: Un enfoque práctico. Revista Mexicana de Ciberseguridad, 10(2), 45-63.
European Union Agency for Cybersecurity (ENISA). (2021). Artificial intelligence for advanced threat detection: Policy recommendations. Bruselas: ENISA.
García, L., & Martínez, A. (2020). Métodos de detección de anomalías en tráfico de red: Comparativa entre técnicas tradicionales y modernas. Revista Iberoamericana de Innovación Tecnológica, 12(4), 22-40.
Gutiérrez, R., & Martínez, A. (2020). Implementación de aprendizaje profundo para la detección de anomalías en entornos empresariales. Revista de Ciencias Empresariales y Cibernéticas, 6(3), 145-160.
ISO/IEC. (2021). ISO/IEC 27032: Guidelines for cybersecurity. Londres: ISO/IEC.
Kim, S., & Park, H. (2019). Deep learning for network anomaly detection: State-of-the-art review. Journal of Cybersecurity Strategies, 7(1), 35-50. https://doi.org/10.1080/00275565.2019.001023
Matus, C., & Pérez, R. (2018). Modelos matemáticos aplicados a la ciberseguridad: Teoría y práctica. Journal of Cyber Analytics, 9(3), 55-68.
Muralidharan, K., & Sukhtankar, S. (2016). Enhancing cybersecurity through adaptive AI models. Journal of Cyber Risk Management, 14(3), 330-355.
Organización Internacional de Normalización (ISO). (2021). ISO 27001: Normas para la gestión de la seguridad de la información. Ginebra: ISO.
Patel, R., & Patel, A. (2018). Enhancing cybersecurity through deep learning approaches. International Journal of Advanced Cyber Systems, 7(1), 28-43. https://doi.org/10.1016/j.ijacs.2018.01.004
Quesada, J., & López, R. (2020). Uso de redes neuronales convolucionales en la ciberseguridad: Casos de éxito. Estudios en Usabilidad y Seguridad Digital, 10(1), 30-45.
Rodríguez, A., & Vargas, L. (2019). Redes neuronales en la detección de ataques: Un análisis técnico. Revista de Gestión Empresarial y Tecnológica, 9(4), 200-219.
Sabharwal, S., & Singhal, R. (2021). Advancing anomaly detection with convolutional and recurrent neural networks. Journal of Machine Learning in Security, 16(3), 220-238. https://doi.org/10.1108/JMLS-09-2021-004
Sandoval, L., & Hernández, R. (2020). Impacto del aprendizaje profundo en la detección de ataques zero-day. Revista Latinoamericana de Ciberseguridad, 8(3), 88-100.
Smith, J., & Taylor, P. (2020). Zero-day attack detection using deep learning: Challenges and solutions. Journal of Advanced Cybersecurity Research, 12(4), 190-208. https://doi.org/10.1002/jacr.2020
Thompson, B., & Green, A. (2019). Improving network security with anomaly-based systems. Journal of Business Systems and Cyber Defense, 8(4), 75-90.
WHO. (2021). Global challenges in cybersecurity and how AI can help. Ginebra: World Health Organization.
World Economic Forum (WEF). (2021). Cyber resilience in the digital age: Building proactive defense systems. Ginebra: WEF.
Downloads
Published
How to Cite
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Ana Laura Barcenas Medina, Alan Jair Alcaraz Cancio
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
