Persona: Pastor Vargas, Rafael
Cargando...
Dirección de correo electrónico
ORCID
0000-0002-4089-9538
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Pastor Vargas
Nombre de pila
Rafael
Nombre
6 resultados
Resultados de la búsqueda
Mostrando 1 - 6 de 6
Publicación Anomaly Detection in Smart Rural IoT Systems(Springer, 2025-06) Fernández Morales, Enrique; Tobarra Abad, María de los Llanos; Robles Gómez, Antonio; Pastor Vargas, Rafael; Vidal Balboa, Pedro; Sarraipa, JoaoThe main contribution of this work is based on the presentation of new AI models for the detection of attacks, within IoT systems using an extensive and complete dataset. In this context, we evaluate not only the performance of the models in terms of detection of attacks, but also their resource consumption, such as the time needed to analyze a sample, the consumption of computing cycles to analyze a sample, as well as the hard disk usage to store the AI models. Its application is oriented to the context of IoT systems in rural environments, where devices deployed in these environments usually have strong restrictions on these resources. Our results indicate that the OPTIMIST-LSTM model offers the best balance between accuracy and generalization, whereas XAI-IoT stands out for its computational efficiency, making them the most suitable for implementation in IoT infrastructures with limited resources.Publicación Assessing Feature Selection Techniques for AI-based IoT Network Intrusion Detection(Springer, 2025-06) García Merino, José Carlos; Tobarra Abad, María de los Llanos; Robles Gómez, Antonio; Pastor Vargas, Rafael; Vidal Balboa, Pedro; Dionisio Rocha, André; Jardim Gonçalves, RicardoThe widespread adoption of Internet of Things (IoT) technology in rural areas has led to qualitative leaps in fields such as agriculture, livestock farming, and transportation, giving rise to the concept of Smart Rural. However, Smart Rural IoT ecosystems are often vulnerable to cyberattacks. Although Artificial Intelligence (AI) based intrusion detection systems offer an effective solution to protect these environments, IoT devices are typically constrained in terms of memory and computation capabilities, making it essential to optimise the computational burden of AI models. This work explores different feature selection techniques to develop compact and fast Random Forest models for anomaly detection in IoT environments. The obtained results demonstrate that appropriate feature selection can reduce model size and inference time by at least 45% and 8%, respectively, without compromising predictive performance.Publicación Comprehensive AI-Driven Privacy Risk Assessment in Mobile Apps and Social Networks(Springer, 2025-09-29) Blanco Aza, Daniel; Robles Gómez, Antonio; Pastor Vargas, Rafael; Tobarra Abad, María de los Llanos; Vidal Balboa, Pedro; Méndez-Suárez, MarianoThe pervasive use of mobile applications and social networks has intensified privacy concerns due to the widespread collection, processing, and sharing of personal data. To address these challenges, we introduce SafeMountain, a novel AI-driven framework designed to systematically quantify, evaluate, and visualize privacy risks in mobile apps and social platforms, ensuring strict compliance with international regulations, particularly the General Data Protection Regulation (GDPR). SafeMountain combines static and dynamic code analyses to scrutinize real-world data handling practices and detect potential privacy breaches. It also employs advanced Natural Language Processing (NLP) techniques for automated interpretation and evaluation of privacy policies and Terms of Service. By mapping textual policy disclosures to actual app permissions and behaviors, it identifies discrepancies and highlights potential non-compliance and data misuse. The framework introduces an objective risk scoring mechanism aligned with international standards and regulatory requirements, offering a structured methodology to classify and visualize privacy risks. This risk assessment spans multiple dimensions (predictability, manageability, and disassociability) leveraging privacy engineering principles and regulatory risk factors, and uses an intuitive traffic-light system (Green, Yellow, Red) to enhance transparency and user comprehension. SafeMountain addresses major research gaps, notably the absence of standardized privacy risk scoring and comprehensive visualization tools. By delivering actionable insights into permission consistency, policy transparency, compliance gaps, and data leakage vulnerabilities, it empowers users, developers, and organizations to manage privacy risks proactively. Ultimately, SafeMountain fosters trust through more transparent and accountable data privacy practices across digital ecosystems.Publicación An Efficient Feature Selection Framework Using Genetic Algorithms for AI-Driven IDS in IoT Environments(Springer, 2025-12-01) García Merino, José Carlos; Tobarra Abad, María de los Llanos; Robles Gómez, Antonio; Pastor Vargas, Rafael; Vidal Balboa, PedroThe increasing concern over Internet of Things (IoT) cybersecurity, driven by the growing number of connected devices and their vulnerability to attacks, has intensified the demand for effective Intrusion Detection Systems (IDSs). In recent years Artificial Intelligence (AI) solutions has emerged as a common approach in modern cybersecurity systems, offering powerful tools for detecting complex patterns and threats. However, the limited computing capabilities of IoT environments require models that are not only accurate but also resource-efficient. Feature selection (FS) plays a key role in this context, but traditional techniques such as the Chi-2 test and mutual information focus only on predictive performance, overlooking important practical concerns like inference time and model size. In this work, we propose a novel FS approach based on a custom scoring function that combines accuracy with penalties for inference time and model size. This metric is integrated into a Genetic Algorithm framework to guide the search for optimal feature subsets. The proposed method is evaluated on the NF-ToN-IoT-v2 dataset against standard techniques. Results demonstrate that our approach achieves competitive predictive performance while significantly reducing inference time and model size, highlighting the relevance of considering deployment-oriented metrics in the FS processPublicación Privacy Analysis in Mobile Apps and Social Networks Using AI Techniques(IEEE - Institute of Electrical and Electronics Engineers, 2024-09-17) Blanco Aza, Daniel; Robles Gómez, Antonio; Pastor Vargas, Rafael; Tobarra Abad, María de los Llanos; Vidal Balboa, Pedro; Méndez Suárez, MarianoIn the current landscape of mobile applications and social networks, privacy concerns have become paramount due to the extensive collection and processing of personal data. Therefore, this paper presents a comprehensive review of the state-of-the-art on automated privacy risk analysis in mobile applications and social networks. This review includes various methodologies, tools and frameworks that use ML and NLP systems to assess and ensure compliance with privacy regulations, such as the GDPR. Through a careful application of the PRISMA methodology, key studies have been systematically analyzed. Our findings reveal significant progress in the integration of automated techniques for assessing privacy risks.Publicación Internet of Things Platform for Assessment and Research on Cybersecurity of Smart Rural Environments(MDPI, 2025-08-01) Sernández Iglesias, Daniel; Tobarra Abad, María de los Llanos; Pastor Vargas, Rafael; Robles Gómez, Antonio; Vidal Balboa, Pedro; Sarraipa, João; Instituto Nacional de Ciberseguridad (INCIBE); (NextGenerationEU/PRTR) Unión EuropeaRural regions face significant barriers to adopting IoT technologies, due to limited connectivity, energy constraints, and poor technical infrastructure. While urban environments benefit from advanced digital systems and cloud services, rural areas often lack the necessary conditions to deploy and evaluate secure and autonomous IoT solutions. To help overcome this gap, this paper presents the Smart Rural IoT Lab, a modular and reproducible testbed designed to replicate the deployment conditions in rural areas using open-source tools and affordable hardware. The laboratory integrates long-range and short-range communication technologies in six experimental scenarios, implementing protocols such as MQTT, HTTP, UDP, and CoAP. These scenarios simulate realistic rural use cases, including environmental monitoring, livestock tracking, infrastructure access control, and heritage site protection. Local data processing is achieved through containerized services like Node-RED, InfluxDB, MongoDB, and Grafana, ensuring complete autonomy, without dependence on cloud services. A key contribution of the laboratory is the generation of structured datasets from real network traffic captured with Tcpdump and preprocessed using Zeek. Unlike simulated datasets, the collected data reflect communication patterns generated from real devices. Although the current dataset only includes benign traffic, the platform is prepared for future incorporation of adversarial scenarios (spoofing, DoS) to support AI-based cybersecurity research. While experiments were conducted in an indoor controlled environment, the testbed architecture is portable and suitable for future outdoor deployment. The Smart Rural IoT Lab addresses a critical gap in current research infrastructure, providing a realistic and flexible foundation for developing secure, cloud-independent IoT solutions, contributing to the digital transformation of rural regions.