Mario Vega-Barbas

Dr. Mario Vega-Barbas

Universidad Politécnica de Madrid
orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 January 2021 in Sensors
Verified
Journal Article
Open access
PDF file
XLXavier A Larriva-Novo
Xavier A Larriva-Novo
Víctor VillagráVíctor Villagrá
Víctor Villagrá
Mario Vega-BarbasMario Vega-Barbas
Mario Vega-Barbas
Diego RiveraDiego Rivera
Diego Rivera
MRMario Sanz Rodrigo
Mario Sanz Rodrigo
Security in IoT networks is currently mandatory, due to the high amount of data that has to be handled. These systems are vulnerable to several cybersecurity attacks, which are increasing in number and sophistication. Due to this reason, new intrusion detection techniques have to be developed, being as accurate as possible for these scenarios. Intrusion detection systems based on machine learning algorithms have already shown a high performance in terms of accuracy. This research proposes the study and evaluation of several preprocessing techniques based on traffic categorization for a machine learning neural network algorithm. This research uses for its evaluation two benchmark datasets, namely UGR16 and the UNSW-NB15, and one of the most used datasets, KDD99. The preprocessing techniques were evaluated in accordance with scalar and normalization functions. All of these preprocessing models were applied through different sets of characteristics based on a categorization composed by four groups of features: basic connection features, content characteristics, statistical characteristics and finally, a group which is composed by traffic-based features and connection direction-based traffic characteristics. The objective of this research is to evaluate this categorization by using various data preprocessing techniques to obtain the most accurate model. Our proposal shows that, by applying the categorization of network traffic and several preprocessing techniques, the accuracy can be enhanced by up to 45%. The preprocessing of a specific group of characteristics allows for greater accuracy, allowing the machine learning algorithm to correctly classify these parameters related to possible attacks.

1 January 2020 in IEEE Access
Verified
Journal Article
Open access
XLXavier A Larriva-Novo
Xavier A Larriva-Novo
Mario Vega-BarbasMario Vega-Barbas
Mario Vega-Barbas
Víctor VillagráVíctor Villagrá
Víctor Villagrá
MRMario Sanz Rodrigo
Mario Sanz Rodrigo
Artificial intelligence algorithms have a leading role in the field of cybersecurity and attack detection, being able to present better results in some scenarios than classic intrusion detection systems such as Snort or Suricata. In this sense, this research focuses on the evaluation of characteristics for different well-established Machine Leaning algorithms commonly applied to IDS scenarios. To do this, a categorization for cybersecurity data sets that groups its records into several groups is first considered. Making use of this division, this work seeks to determine which neural network model (multilayer or recurrent), activation function, and learning algorithm yield higher accuracy values, depending on the group of data. Finally, the results are used to determine which group of data from a cybersecurity data set are more relevant and representative for the intrusion detection, and the most suitable configuration of Machine Learning algorithm to decrease the computational load of the system.

6 December 2022 in Future Generation Computer Systems
Verified
Journal Article
Open access
Carmen Sanchez-ZasCarmen Sanchez-Zas
Carmen Sanchez-Zas
VVVíctor A. Villagrá
Víctor A. Villagrá
Mario Vega-BarbasMario Vega-Barbas
Mario Vega-Barbas
XLXavier Larriva-Novo
Xavier Larriva-Novo
JMJosé Ignacio Moreno
José Ignacio Moreno
JBJulio Berrocal
Julio Berrocal

15 May 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XLXavier A Larriva-Novo
Xavier A Larriva-Novo
Mario Vega-BarbasMario Vega-Barbas
Mario Vega-Barbas
Víctor VillagráVíctor Villagrá
Víctor Villagrá
Diego RiveraDiego Rivera
Diego Rivera
Manuel Alvarez-CampanaManuel Alvarez-Campana
Manuel Alvarez-Campana
FBFundetel Berrocal
Fundetel Berrocal
New computational and technological paradigms that currently guide developments in the information society, i.e., Internet of things, pervasive technology, or Ubicomp, favor the appearance of new intrusion vectors that can directly affect people’s daily lives. This, together with advances in techniques and methods used for developing new cyber-attacks, exponentially increases the number of cyber threats which affect the information society. Because of this, the development and improvement of technology that assists cybersecurity experts to prevent and detect attacks arose as a fundamental pillar in the field of cybersecurity. Specifically, intrusion detection systems are now a fundamental tool in the provision of services through the internet. However, these systems have certain limitations, i.e., false positives, real-time analytics, etc., which require their operation to be supervised. Therefore, it is necessary to offer architectures and systems that favor an efficient analysis of the data handled by these tools. In this sense, this paper presents a new model of data preprocessing based on a novel distributed computing architecture focused on large-scale datasets such as UGR’16. In addition, the paper analyzes the use of machine learning techniques in order to improve the response and efficiency of the proposed preprocessing model. Thus, the solution developed achieves good results in terms of computer performance. Finally, the proposal shows the adequateness of decision tree algorithms for training a machine learning model by using a large dataset when compared with a multilayer perceptron neural network.

1 July 2012
Verified
Conference Paper
Closed access
Mario Vega-BarbasMario Vega-Barbas
Mario Vega-Barbas
DCDiego Casado-Mansilla
Diego Casado-Mansilla
MVMiguel A. Valero
Miguel A. Valero
Diego López-de-IpiñaDiego López-de-Ipiña
Diego López-de-Ipiña
Jose BravoJose Bravo
Jose Bravo
Francisco Florez-RevueltaFrancisco Florez-Revuelta
Francisco Florez-Revuelta
The presented work aims to contribute towards the standardization and the interoperability off the Future Internet through an open and scalable architecture design. We present S 3 OiA as a syntactic/semantic Service-Oriented Architecture that allows the integration of any type of object or device, not mattering their nature, on the Internet of Things. Moreover, the architecture makes possible the use of underlying heterogeneous resources as a substrate for the automatic composition of complex applications through a semantic Triple Space paradigm. Created applications are dynamic and adaptive since they are able to evolve depending on the context where they are executed. The validation scenario of this architecture encompasses areas which are prone to involve human beings in order to promote personal autonomy, such as home-care automation environments and Ambient Assisted Living.

23 January 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
Farhad AbtahiFarhad Abtahi
Farhad Abtahi
FSFernando Seoane
Fernando Seoane
IPIván Pau
Iván Pau
Mario Vega-BarbasMario Vega-Barbas
Mario Vega-Barbas
Background: Health care artificial intelligence (AI) systems are increasingly integrated into clinical workflows, yet remain vulnerable to data-poisoning attacks. A small number of manipulated training samples can compromise AI models used for diagnosis, documentation, and resource allocation. Existing privacy regulations, including the Health Insurance Portability and Accountability Act and the General Data Protection Regulation, may inadvertently complicate anomaly detection and cross-institutional auditing, thereby limiting visibility into adversarial activity. Objective: This study provides a comprehensive threat analysis of data poisoning vulnerabilities across major health care AI architectures. The goals are to (1) identify attack surfaces in clinical AI systems, (2) evaluate the feasibility and detectability of poisoning attacks analytically modeled in prior security research, and (3) propose a multilayered defense framework appropriate for health care settings. Methods: We synthesized empirical findings from 41 key security studies published between 2019 and 2025 and integrated them into an analytical threat-modeling framework specific to health care. We constructed 8 hypothetical yet technically grounded attack scenarios across 4 categories: (1) architecture-specific attacks on convolutional neural networks, large language models, and reinforcement learning agents (scenario A); (2) infrastructure exploitation in federated learning and clinical documentation pipelines (scenario B); (3) poisoning of critical resource allocation systems (scenario C); and (4) supply chain attacks affecting commercial foundation models (scenario D). Scenarios were aligned with realistic insider-access threat models and current clinical deployment practices. Results: Multiple empirical studies demonstrate that attackers with access to as few as 100-500 poisoned samples can compromise health care AI systems, with attack success rates typically ≥60%. Critically, attack success depends on the absolute number of poisoned samples rather than their proportion of the training corpus, a finding that fundamentally challenges assumptions that larger datasets provide inherent protection. We estimate that detection delays commonly range from 6 to 12 months and may extend to years in distributed or privacy-constrained environments. Analytical scenarios highlight that (1) routine insider access creates numerous injection points across health care data infrastructure, (2) federated learning amplifies risks by obscuring attribution, and (3) supply chain compromises can simultaneously affect dozens to hundreds of institutions. Privacy regulations further complicate cross-patient correlation and model audit processes, substantially delaying the detection of subtle poisoning campaigns. Conclusions: Health care AI systems face significant security challenges that current regulatory frameworks and validation practices do not adequately address. We propose a multilayered defense strategy that combines ensemble disagreement monitoring, adversarial testing, privacy-preserving yet auditable mechanisms, and strengthened governance requirements. Ensuring patient safety may require a shift from opaque, high-performance models toward more interpretable and constraint-driven architectures with verifiable robustness guarantees.