Pasar al contenido principal

OPTIMIZACION DE REDES WLAN COORDINADAS DE ULTIMA GENERACION BASADAS EN ARQUITECTURAS PROGRAMABLES Y VIRTUALIZADAS (NEWLAN)

PID2022-136476OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ZARAGOZA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Empirical evaluation of feature selection methods for machine learning based intrusion detection in IoT scenarios

  • García, José
  • Entrena, Jorge
  • Alesanco, Álvaro
This paper delves into the critical need for enhanced security measures within the Internet of Things (IoT) landscape due to inherent vulnerabilities in IoT devices, rendering them susceptible to various forms of cyber-attacks. The study emphasizes the importance of Intrusion Detection Systems (IDS) for continuous threat monitoring. The objective of this study was to conduct a comprehensive evaluation of feature selection (FS) methods using various machine learning (ML) techniques for classifying traffic flows within datasets containing intrusions in IoT environments. An extensive benchmark analysis of ML techniques and FS methods was performed, assessing feature selection under different approaches including Filter Feature Ranking (FFR), Filter-Feature Subset Selection (FSS), and Wrapper-based Feature Selection (WFS). FS becomes pivotal in handling vast IoT data by reducing irrelevant attributes, addressing the curse of dimensionality, enhancing model interpretability, and optimizing resources in devices with limited capacity. Key findings indicate the outperformance for traffic flows classification of certain tree-based algorithms, such as J48 or PART, against other machine learning techniques (naive Bayes, multi-layer perceptron, logistic, adaptive boosting or k-Nearest Neighbors), showcasing a good balance between performance and execution time. FS methods' advantages and drawbacks are discussed, highlighting the main differences in results obtained among different FS approaches. Filter-feature Subset Selection (FSS) approaches such as CFS could be more suitable than Filter Feature Ranking (FFR), which may select correlated attributes, or than Wrapper-based Feature Selection (WFS) methods, which may tailor attribute subsets for specific ML techniques and have lengthy execution times. In any case, reducing attributes via FS has allowed optimization of classification without compromising accuracy. In this study, F1 score classification results above 0.99, along with a reduction of over 60% in the number of attributes, have been achieved in most experiments conducted across four datasets, both in binary and multiclass modes. This work emphasizes the importance of a balanced attribute selection process, taking into account threat detection capabilities and computational complexity.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Performance trade-offs of auto scaling schemes for NFV with reliability requirements

  • Perez-Valero, Jesus
  • Garcia-Reinoso, Jaime
  • Banchs, Albert
  • Serrano, Pablo
  • Ortin, Jorge
  • Costa-Perez, Xavier
A major concern for future mobile networks is to meet extremely stringent reliability requirements without incurring very high energy consumption. To this aim, we need auto-scaling techniques to switch on/off servers on demand, ensuring that they are active when required. One key challenge is to keep the right number of active servers while accounting for both the fallibility of servers and their non-zero boot up time: if this number is too small we risk service disruption, but if it is too large resources will be wasted. In this paper, we analyze this challenge by assessing the performance of different strategies to support an energy-efficient highly-reliable service, which range from deploying few blade (i.e., reliable) servers to deploying many nano (i.e., unreliable) servers. Our main take-away message is two-fold: (1) a server farm of nano servers can provide a more energy efficient operation than a farm of blade servers, but (2) it involves a very dynamic operation both in terms of task migrations and (de)activations, which challenges the endurance of the hardware.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Modeling the Coexistence of LECIM ALOHA PCA and CSMA/CA in Unslotted IEEE 802.15.4 Networks

  • Ortín, Jorge
  • Gállego, José Ramón
  • Canales, María
Wireless sensor networks are pivotal in critical infrastructure monitoring due to their cost-effectiveness and real-time data processing capabilities. The IEEE 802.15.4 standard, especially the Low Energy Critical Infrastructure Monitoring (LECIM) portions, plays a crucial role in enhancing monitoring efficiency of critical infrastructure. LECIM introduces Priority Channel Access (PCA) for traffic prioritization, particularly beneficial for critical information transmission. This paper investigates the coexistence of CSMA/CA-based nodes transmitting non-priority data and LECIM ALOHA PCA nodes handling critical information in unslotted IEEE 802.15.4 networks. We propose a novel theoretical framework to evaluate the performance of a heterogeneous LECIM network, where some nodes use the CSMA/CA channel access method while others use LECIM ALOHA PCA. The performance is measured in terms of reliability, delay and power consumption. Validation of the theoretical framework is conducted using a system-level simulator.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A Novel Dataset for Early Cardiovascular Risk Detection in School Children Using Machine Learning

  • Olivera Solís, Rafael Alejandro
  • González Rodríguez, Emilio Francisco
  • Castañeda Sheissa, Roberto
  • Lorenzo-Ginori, Juan Valentín
  • García, José
This study introduces the PROCDEC dataset, a novel collection of 1140 cases with 30 cardiovascular risk factors gathered over a 10-year period from school children in Santa Clara, Cuba. The dataset was curated with input from medical experts in pediatric cardiology, endocrinology, general medicine, and clinical laboratory, ensuring its clinical relevance. We conducted a rigorous performance evaluation of 10 machine learning (ML) algorithms to classify cardiovascular risk into two categories: at risk and not at risk. The models were assessed using a stratified k-fold cross-validation approach to enhance the reliability of the findings. Among the evaluated models—Bayes Net, Naive Bayes, SMO, K-Nearest Neighbors (KNN), Logistic Regression, AdaBoost, Multilayer Perceptron (MLP), J48, Logistic Model Tree (LMT), and Random Forest (RF)—the best-performing classifiers (MLP, LMT, J48 and Logistic Regression) achieved F1-score values exceeding 0.83, indicating strong predictive capability. To improve interpretability, we employed feature selection techniques to rank the most influential risk factors. Key contributors to classification performance included hypertension, hyperreactivity, body mass index (BMI), uric acid, cholesterol, parental hypertension, and sibling dyslipidemia. These findings align with established clinical knowledge and reinforce the potential of ML models for pediatric cardiovascular risk assessment. Unlike previous studies, our research not only evaluates multiple ML techniques but also emphasizes their clinical applicability and interpretability, which are critical for real-world implementation. Future work will focus on validating these models with external datasets and integrating them into decision-support systems for early risk detection.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A Deep Learning Approach for Multiclass Attack Classification in IoT and IIoT Networks Using Convolutional Neural Networks

  • Seyedkolaei, Ali Abdi
  • Mahmoudi, Fatemeh
  • García, José
The rapid expansion of the Internet of Things (IoT) and industrial Internet of Things (IIoT) ecosystems has introduced new security challenges, particularly the need for robust intrusion detection systems (IDSs) capable of adapting to increasingly sophisticated cyberattacks. In this study, we propose a novel intrusion detection approach based on convolutional neural networks (CNNs), designed to automatically extract spatial patterns from network traffic data. Leveraging the DNN-EdgeIIoT dataset, which includes a wide range of attack types and traffic scenarios, we conduct comprehensive experiments to compare the CNN-based model against traditional machine learning techniques, including decision trees, random forests, support vector machines, and K-nearest neighbors. Our approach consistently outperforms baseline models across multiple performance metrics—such as F1 score, precision, and recall—in both binary (benign vs. attack) and multiclass settings (6-class and 15-class classification). The CNN model achieves F1 scores of 1.00, 0.994, and 0.946, respectively, highlighting its strong generalization ability across diverse attack categories. These results demonstrate the effectiveness of deep-learning-based IDSs in enhancing the security posture of IoT and IIoT infrastructures, paving the way for intelligent, adaptive, and scalable threat detection systems.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Legacy-Compatible Multi-User Wi-Fi Aggregation for Enhanced Downlink Efficiency and Security

  • Salazar-Riaño, J.-L.
  • Fernández-Navajas, J.
  • Hernández-Solana, A.
  • Ruíz-Mas, J.
  • Azuara-Guillén, G.
  • Cajal-Pérez, R.
This work introduces a novel Wi-Fi frame aggregation mechanism that enables efficient multiuser downlink transmissions in IEEE 802.11 networks (including earlier standards). We focus on exploring feasible and practical approaches to enable or approximate multi-user aggregation by leveraging existing features, while ensuring the compatibility with legacy standards. The proposed approach, implemented and evaluated on a real-world testbed, allows the Access Point (AP) to aggregate MAC Service Data Units (MSDUs) destined for multiple users/stations, using a scheme based on Multichannel Broadcast Encryption of Short Messages. It is particularly effective in scenarios involving a high volume of small data packets to multiple users/stations and where communication reliability is critical to maintaining high-quality service. This innovative solution not only extends and improves the efficiency of standard aggregation schemes in such scenarios but also enables efficient multi-user downlink transmissions and enhances security by strengthening the protection of transmitted data.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Evaluating large language models effectiveness for flow-based intrusion detection: a comparative study with ML and DL baselines

  • Mehavilla, Lorena
  • Rodríguez, María
  • García, José
  • Alesanco, Álvaro
This paper presents the first systematic benchmark evaluating Large Language Models (LLMs), specifically GPT-2, GPT-Neo-125M, and LLaMA-3.2-1B, as standalone classifiers for intrusion detection, covering both binary and multiclass classification tasks, using structured Zeek logs derived from the CIC IoT 2023 dataset. We compare their performance against established and widely used Machine Learning (XGBoost, Random Forest, Decision Tree) and Deep Learning models (MLP, GRU, LeNet-5) across key evaluation metrics: detection effectiveness (precision, recall and F1-score), inference speed, and resource consumption. All models are consistently trained and rigorously evaluated on the CIC IoT 2023 dataset, ensuring fair, reproducible, and transparent comparisons. Our findings indicate that while LLMs achieve strong F1-score exceeding 95%, and do not fully utilize available GPU resources, they still do not outperform top-performing ML models. Notably XGBoost achieves a higher F1-score of 96.96%, using only 4% of the available CPU. These results emphasize the practical trade-offs between detection capability, inference efficiency, and hardware requirements when applying LLMs in flow-based IDS contexts, particularly in resource-constrained environments such as IoT or edge deployments.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Unveiling user activities on instant messaging platforms: A study of activity fingerprinting through traffic analysis and machine learning techniques

  • Mehavilla, Lorena
  • García, José
  • Alesanco, Álvaro
Encrypted instant messaging (IM) traffic conceals message content but still exposes communication patterns that can reveal user behaviour. This paper presents a unified framework for inferring user activities across multiple IM platforms by analysing encrypted traffic using machine learning techniques. The proposed approach integrates empirical traffic characterisation, transaction-centric segmentation, and lightweight classifiers to detect user actions, such as sending or receiving text and multimedia messages, in real time. Using Zeek as the core analysis engine, the framework performs packet inspection, transaction segmentation, connection classification, and feature extraction. The framework was evaluated on traffic from nine major IM platforms (Discord, Facebook Messenger, Instagram, Snapchat, Microsoft Teams, Telegram, WeChat, WhatsApp, and X), achieving F1 scores ranging from 0.62 for X up to 0.98 for WhatsApp. Unlike prior studies limited to single applications or synthetic datasets, our work employs realistic, user-driven traffic and explicitly distinguishes message type and direction, improving comparison and cross-platform generalization. Beyond methodological advancements, this study exposes privacy risks inherent in encrypted communication and outlines ethical safeguards and countermeasures to mitigate activity fingerprinting. The findings demonstrate that accurate, real-time inference of encrypted messaging activities is feasible under responsible, consent-based conditions, offering valuable insights for network forensics and privacy-aware communication design.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Practical challenges of implementing a hybrid ISS-QoSS RAN slicing in SDN WLAN networks

  • Hernández-Solana, Ángela
  • Ruiz-Mas, José
  • Canales, María
  • Fernández-Navajas, Julian
  • Gállego, José Ramón
  • Ibáñez-Alloza, Sara
Network slicing is a key feature in 4G and 5G mobile networks and, more recently, IEEE 802.11 networks. This paper proposes a hybrid Infrastructure Sharing Slicing (ISS) and Quality of Service Sharing Slicing (QoSS) solution, adapting the Airtime Deficit Weighted Round Robin (ADWRR) scheduling. The approach ensures isolation and resource segmentation among tenants or client categories, along with fine-grained traffic differentiation, prioritization or resource isolation for various service classes within slices. It includes local adaptations of allocated partitions/portions of airtime, a.k.a. quantum, at the two levels (ISS-QoSS) to improve specific QoS requirements by modifying the natural ADWRR airtime reallocation. The RAN slicing functions are implemented and tested on a Software Defined Networking (SDN) experimental prototype using an open-source framework combining centralized and distributed components. The technical focus is on practical challenges affecting local-level implementation efficiency and feasibility.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Leveraging Kubernetes for Automated Deployment and Orchestration in Virtualized Wi-Fi Networks

  • Canales, María
  • Gállego, José Ramón
  • Santacruz, Julia
  • Ruiz-Mas, José
  • Hernández-Solana, Ángela
  • Fernández-Navajas, Julián
  • Ortín, Jorge
The increasing prevalence of wireless devices has led to the widespread adoption of Wi-Fi networks. This demand has driven the development of solutions that involve the coordinated management of Access Points. In recent years, Software-Defined Wireless Networks (SDWNs) have emerged as a promising approach, leveraging Software-Defined Networking (SDN) principles to enable intelligent coordination and management of APs using cost-effective hardware. However, while SDWNs have primarily focused on managing the radio interface, less attention has been devoted to SDN-based management of wired network segments or the automated deployment of virtualized Wi-Fi infrastructures. In this work, we present a fully virtualized Wi-Fi network solution that integrates SDN and Network Function Virtualization (NFV) principles across both wireless and wired segments. Our architecture features SDN-based data plane management, two SDN controllers, virtualized APs, and a virtualized gateway, all implemented as containerized components. Automated deployment and orchestration are facilitated using Kubernetes. This infrastructure provides a robust foundation for implementing advanced end-to-end functionalities, such as network slicing, thereby preparing Wi-Fi networks for seamless integration into future 5G and 6G ecosystems.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A Deception-Based Access Control Mechanism for Protecting PLCs from ModbusTCP Brute-Force Attacks in IIoT Environments

  • AbdulJawad, Mohammad
  • Masoud, Mohammad Z.
  • Álesanco, Álvaro
  • García, José
Industrial control systems (ICSs) increasingly rely on legacy communication protocols such as ModbusTCP, which lack built-in security mechanisms and remain widely exposed to network-based attacks. This paper investigates the security limitations of authentication mechanisms in ModbusTCP-enabled programmable logic controllers (PLCs) and demonstrates how plaintext credential transmission and limited connection handling capabilities can be exploited to perform brute-force and denial-of-service (DoS) attacks. An experimental testbed based on two industrial Delta PLC families (DVP-13SE and DVP-311SV3) was developed to systematically evaluate these vulnerabilities under realistic conditions. The results show that authentication credentials can be easily captured through network sniffing, while the PLC communication stack supports a maximum of 16 concurrent connections and can process up to approximately 8600 Modbus operations per second, making it susceptible to resource exhaustion and performance degradation under distributed attack scenarios. To address these limitations, this paper proposes a lightweight deception-based protection mechanism, termed the PLC misleading algorithm (PMA), which is implemented directly within the PLC ladder logic. Unlike traditional network-level defenses, PMA operates at the device level and dynamically misleads attackers by generating controlled randomized responses while preserving consistent behavior for legitimate clients. Experimental results demonstrate that PMA significantly mitigates brute-force effectiveness by preventing reliable password extraction while introducing minimal overhead (2.2% memory usage) and maintaining acceptable communication latency. Additionally, the proposed approach significantly reduces observable attack traffic, with only 0.246 Modbus operations per second observed during the attack phase, thereby limiting the effectiveness of automated exploitation tools. These findings highlight the potential of in-device deception mechanisms as a practical and deployable security layer for legacy industrial systems, and provide new insights into the resilience of PLC-based infrastructures against network-level attacks. This work bridges the gap between lightweight PLC-level protections and the growing need for robust cybersecurity mechanisms in industrial IoT environments.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Optimized placement of security controllers for enhancing intrusion detection and resilience in software-defined IoT networks

  • Abdi Seyedkolaei, Ali
  • García, José
This study investigates the optimal placement of security controllers in Software-Defined IoT (SD-IoT) networks to enhance intrusion detection and improve network resilience against cyber threats. In SD-IoT environments, the strategic positioning of security controllers plays a vital role in monitoring malicious activity and responding to attacks effectively. However, inefficient controller placement can increase detection time, heighten vulnerability, and degrade overall network performance. To address this challenge, we propose multi-objective optimization approach based on the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to determine the optimal number and locations of security controllers. The proposed method simultaneously considers network topology, resource constraints, and the characteristics of potential attack patterns to minimize intrusion detection delay, reduce the impact of threats on data transmission, and enhance load distribution. For evaluation, simulations were conducted using topologies from the Internet Topology Zoo. The proposed method was compared against other existing methods, such as Random Placement, Greedy Algorithm and Iterated Local Search strategies, in terms of controllers required, security, latency, load balancing, and deployment cost. Results demonstrate that our approach significantly outperforms other methods, for instance achieving approximately a 60% reduction in deployment cost in the large-scale Cogentco topology. These findings highlight the effectiveness of integrating NSGA-II for strategic controller placement to strengthen security and operational efficiency in SD-IoT networks.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A rule-based label harmonization framework for cross-dataset IoT intrusion detection

  • Rodríguez, María
  • Mehavilla, Lorena
  • Alesanco, Álvaro
  • García, José
Machine learning (ML) has become a dominant approach for intrusion detection in Internet of Things (IoT) networks, yet most studies evaluate models within a single dataset, overlooking generalization across heterogeneous environments. This work revisits that challenge through a systematic cross-dataset evaluation using three public datasets: CIC-IoT-2023, IoT-23, and IoTID20. When trained and tested within the same dataset, models achieved near-perfect accuracy (average F1 > 0.99); however, performance degraded sharply when models trained on one dataset were tested on a different one (average F1 < 0.50 except for Multi-Layer Perceptron). Combining multiple datasets into a unified training corpus restored high accuracy (average F1 > 0.99) however, these results must be interpreted with caution, as consistent labeling remains essential for reliable cross-dataset evaluation. These findings highlight the fragility of current Intrusion Detection System (IDS) models to domain shifts and the promise of dataset fusion for enhancing generalization. We introduce a reproducible framework that harmonizes heterogeneous datasets through rule-based labeling grounded in Zeek’s standardized flow features and MITRE ATT&CK / CAPEC semantics. This replaces manual relabeling with a systematic, extensible procedure, enabling diverse traffic to be transformed into interoperable annotations. Labels are assigned by behavioral characteristics rather than dataset-specific categories, allowing discovery of previously unlabeled malicious activity. A proof of concept with three smart-home environments demonstrated the framework: models maintained near-perfect performance when trained on individual or unified datasets (average F1 > 0.99). Overall, unified rule-based labeling enables scalable dataset reuse, improves cross-dataset generalization, and fosters interpretable, data-centric ML for IoT intrusion detection.