Pro-ZD: A Transferable Graph Neural Network Approach for Proactive Zero-Day Threats Mitigation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Basta, Nardine, Hmida, Firas Ben, Jmal, Houssem, Ikram, Muhammad, Kaafar, Mohamed Ali, Walker, Andy
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908818334547968
author Basta, Nardine
Hmida, Firas Ben
Jmal, Houssem
Ikram, Muhammad
Kaafar, Mohamed Ali
Walker, Andy
author_facet Basta, Nardine
Hmida, Firas Ben
Jmal, Houssem
Ikram, Muhammad
Kaafar, Mohamed Ali
Walker, Andy
contents In today's enterprise network landscape, the combination of perimeter and distributed firewall rules governs connectivity. To address challenges arising from increased traffic and diverse network architectures, organizations employ automated tools for firewall rule and access policy generation. Yet, effectively managing risks arising from dynamically generated policies, especially concerning critical asset exposure, remains a major challenge. This challenge is amplified by evolving network structures due to trends like remote users, bring-your-own devices, and cloud integration. This paper introduces a novel graph neural network model for identifying weighted shortest paths. The model aids in detecting network misconfigurations and high-risk connectivity paths that threaten critical assets, potentially exploited in zero-day attacks -- cyber-attacks exploiting undisclosed vulnerabilities. The proposed Pro-ZD framework adopts a proactive approach, automatically fine-tuning firewall rules and access policies to address high-risk connections and prevent unauthorized access. Experimental results highlight the robustness and transferability of Pro-ZD, achieving over 95% average accuracy in detecting high-risk connections. \
format Preprint
id arxiv_https___arxiv_org_abs_2602_07073
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pro-ZD: A Transferable Graph Neural Network Approach for Proactive Zero-Day Threats Mitigation
Basta, Nardine
Hmida, Firas Ben
Jmal, Houssem
Ikram, Muhammad
Kaafar, Mohamed Ali
Walker, Andy
Cryptography and Security
Artificial Intelligence
Machine Learning
In today's enterprise network landscape, the combination of perimeter and distributed firewall rules governs connectivity. To address challenges arising from increased traffic and diverse network architectures, organizations employ automated tools for firewall rule and access policy generation. Yet, effectively managing risks arising from dynamically generated policies, especially concerning critical asset exposure, remains a major challenge. This challenge is amplified by evolving network structures due to trends like remote users, bring-your-own devices, and cloud integration. This paper introduces a novel graph neural network model for identifying weighted shortest paths. The model aids in detecting network misconfigurations and high-risk connectivity paths that threaten critical assets, potentially exploited in zero-day attacks -- cyber-attacks exploiting undisclosed vulnerabilities. The proposed Pro-ZD framework adopts a proactive approach, automatically fine-tuning firewall rules and access policies to address high-risk connections and prevent unauthorized access. Experimental results highlight the robustness and transferability of Pro-ZD, achieving over 95% average accuracy in detecting high-risk connections. \
title Pro-ZD: A Transferable Graph Neural Network Approach for Proactive Zero-Day Threats Mitigation
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.07073