Pasar al contenido principal

COMPUTACION COLABORATIVA CONECTADA PARA INFRAESTRUCTURAS MULTIDOMINIO HABILITADAS POR IA EN 6G

PID2024-163028OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para la Investigación y el Desarrollo Experimental
Subprograma Subprograma Estatal de Generación de Conocimiento Científico-Técnico y Desarrollo Experimental
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2024
Plan Estatal 2024-2027 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario FUNDACIO PRIVADA I2CAT INTERNET I INNOVACIO DIGITAL A CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

A knowledge-based multi-agent framework for security control recommendation

  • Fernández-Martínez, Carolina
  • Siddiqui, Shuaib
  • Daza, Vanesa
Hardening IT on-premises environments can be a daunting task for teams without access to adequate cybersecurity expertise. In this regard, Decision Support Systems (DSS) with embedded expert knowledge can assist users by guiding them with security recommendations to meet their objectives. This work proposes a Security DSS that recommends security control sub-families given minimal user requirements indicating coverage of different security dimensions. It leverages a curated, unified dataset from both well-known Information Security (InfoSec) and academic sources. This DSS is defined as a non-zero-sum, simultaneous game that is grounded in a Multi-Agent Influence Diagram (MAID) model and explores the decision space over 7 security dimensions or agents, using no-regret online learning to ultimately find the security control sub-families that best fit the requirements while incurring minimal under- and over-provisioning of security resources. This work was validated in terms of performance and accuracy, among others, for varying dataset sizes. It shows exceptional satisfaction coverage results of 99% when using as little as ~65% of the SW-implementable security controls, running in 1.2-35.7 seconds; and more moderate coverage results of 73%-77% when using ~29% of the controls, resolving in 0.8-13.8 seconds., This work was supported by the grant COALESCE-6G PID2024-163028OB-I00, funded by MICIU/AEI/10.13039/501100011033/FEDER, EU
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A knowledge-based multi-agent framework for security control recommendation

  • Fernández-Martínez, Carolina
  • Siddiqui, Shuaib
  • Daza, Vanesa
Hardening IT on-premises environments can be a daunting task for teams without access to adequate cybersecurity expertise. In this regard, Decision Support Systems (DSS) with embedded expert knowledge can assist users by guiding them with security recommendations to meet their objectives. This work proposes a Security DSS that recommends security control sub-families given minimal user requirements indicating coverage of different security dimensions. It leverages a curated, unified dataset from both well-known Information Security (InfoSec) and academic sources. This DSS is defined as a non-zero-sum, simultaneous game that is grounded in a Multi-Agent Influence Diagram (MAID) model and explores the decision space over 7 security dimensions or agents, using no-regret online learning to ultimately find the security control sub-families that best fit the requirements while incurring minimal under- and over-provisioning of security resources. This work was validated in terms of performance and accuracy, among others, for varying dataset sizes. It shows exceptional satisfaction coverage results of 99% when using as little as ~65% of the SW-implementable security controls, running in 1.2-35.7 seconds; and more moderate coverage results of 73%-77% when using ~29% of the controls, resolving in 0.8-13.8 seconds., This work was supported by the grant COALESCE-6G PID2024-163028OB-I00, funded by MICIU/AEI/10.13039/501100011033/FEDER, EU
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

FOM-5G: A Learning-Based Framework for Overload Mitigation in V2X-Enabled 5G Networks

  • Trullenque Ortiz, Martín
  • Camps-Mur, Daniel
  • Sallent, Oriol
  • Nasreddine, Jad
Public networks deploying 5G-Advanced technology are expected to support large-scale connected and cooperative vehicular services. To this end, 3GPP has enabled the deployment of Day 1 V2X safety services over public cellular networks, which provide the global coverage and low latencies these services require. However, high vehicular mobility may result in traffic jams that strain radio resources, leading to cell overload situations that jeopardize the delivery of V2X services. Previous studies have shown that the best action to mitigate cell overloads strongly depends on road topology and the location of the traffic jam with respect to the cell geometry. Moreover, a fundamental insight to address V2X related cell overloads is to realize that the majority of traffic jams are repeatable, hence historical information should be used to take radio resource management (RRM) decisions. In this paper, we present a novel framework for cell overload mitigation in 5G networks (FOM-5G), an RRM solution for ORAN-based public 5G networks that leverages historical information to prevent recurring cell overloads, particularly those affecting V2X services. We validated FOM-5G through comprehensive simulations incorporating three real vehicular mobility patterns from a European city experiencing traffic congestion. The results show that FOM-5G can adapt its congestion control actions to varying traffic conditions, effectively exploit historical data, and achieve superior performance compared to static congestion mitigation approaches., info:eu-repo/semantics/submittedVersion