Pasar al contenido principal

UN NUEVO PARADIGMA PARA EL APRENDIZAJE AUTOMATICO ADVERSARIO

PID2021-124662OB-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 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

RIUMA. Repositorio Institucional de la Universidad de Málaga
Publicación Artículo científico (JournalArticle)

Unlocking the puzzle: non-defining mutations in SARS-CoV-2 proteome may affect vaccine effectiveness.

  • Ulzurrun, Eugenia
  • Grande-Pérez, Ana
  • Del Hoyo, Daniel
  • Guevara, César
  • Gil, Carmen
  • Sorzano, Carlos Óscar
  • Campillo, Nuria E.
Las variantes de SARS-CoV-2 se caracterizan por mutaciones específicas respecto al genoma de Wuhan, pero las mutaciones no definitorias de clado también pueden alterar la estructura y función de las proteínas virales y contribuir al fallo vacunal. El objetivo fue identificar mutaciones en todo el genoma viral asociadas a fallos de vacunación y analizar las propiedades fisicoquímicas de los cambios de aminoácidos resultantes. Se recuperaron secuencias completas del SARS-CoV-2 de pacientes con COVID-19 de GISAID: 7.154 genomas de Italia y 8.819 de España. Las mutaciones con frecuencia ≥10% se agruparon según combinaciones idénticas de aminoácidos. En clados 21L, 22B/22E, 22F/23A (Omicron) y 21J (Delta) se identificaron conjuntos de mutaciones no definitorias asociadas a fallo vacunal. En Italia, cuatro conjuntos incluían combinaciones como L3201F (ORF1a), A27-, I68-, R346T y F486P en la proteína S, y G30- en N. En España, dos conjuntos del clado Delta mostraron mutaciones simultáneas en ORF1a, ORF1b, S y N vinculadas al fallo vacunal. Las dosis de refuerzo ofrecieron una protección ligeramente mayor frente a Omicron. Predominaron sustituciones hidrofóbicas y polares, sugiriendo posibles alteraciones estructurales o funcionales. Los resultados indican que mutaciones no definitorias a lo largo del proteoma viral pueden influir en la eficacia vacunal., SARS-CoV-2 variants are defined by genome-wide mutations relative to the Wuhan strain, yet non–clade-defining mutations may also affect protein structure and contribute to vaccine failure. This study aimed to identify mutations across the full viral genome associated with vaccine failure and assess the physicochemical effects of resulting amino acid changes. Whole-genome sequences from COVID-19 patients were retrieved from GISAID: 7,154 genomes from Italy and 8,819 from Spain. Mutations with ≥10% frequency were grouped by identical amino acid combinations. Non-defining mutations from clades 21L, 22B/22E, 22F/23A (Omicron) and 21J (Delta) were linked to vaccine failure. In Italy, four sequence sets carried combinations such as L3201F (ORF1a), A27-, I68-, R346T and F486P in S, and G30- in N. In Spain, two Delta-associated sets showed concurrent mutations in ORF1a, ORF1b, S and N. Booster doses improved protection modestly against Omicron. Hydrophobic and polar substitutions were predominant, suggesting structural or functional impact. These findings indicate that non–clade-defining mutations across the SARS-CoV-2 proteome may influence vaccine effectiveness., European Commission – NextGenerationEU (Regulation EU 2020/2094), CSIC – Global Health Platform (PTI Salud Global), MCIN/AEI (Ministerio de Ciencia e Innovación / Agencia Estatal de Investigación), FEDER – A way to make Europe, AXA–ICMAT Chair in Adversarial Risk Analysis, Consejería de Economía y Conocimiento, Junta de Andalucía, Programa Operativo FEDER 2014–2020
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A Bayesian network model for predicting cardiovascular risk

  • Ordovas, J M
  • Ríos Insua, David
  • Santos-Lozano, A
  • Lucia, Alejandro
  • Torres, A
  • Kosgodagan, A
  • Camacho, J M
Cardiovascular diseases are the leading death cause in Europe and entail large treatment costs. Cardiovascular risk prediction is crucial for the management and control of cardiovascular diseases. Based on a Bayesian network built from a large population database and expert judgment, this work studies interrelations between cardiovascular risk factors, emphasizing the predictive assessment of medical conditions, and providing a computational tool to explore and hypothesize such interrelations., This work was supported by the AXA-ICMAT Chair in Adversarial Risk Analysis; the Spanish Ministry of Science program PID2021–124662OB-I00; the Spanish Ministry of Economy and Competitiveness and FEDER funds from the European Union [Grant PI18/00139]., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Adversarial Machine Learning: Bayesian Perspectives

  • Ríos Insua, David
  • Naveiro, Roi
  • Gallego, Víctor
  • Poulos, Jason
Adversarial Machine Learning (AML) is emerging as a major field aimed at protecting Machine Learning (ML) systems against security threats: in certain scenarios there may be adversaries that actively manipulate input data to fool learning systems. This creates a new class of security vulnerabilities that ML systems may face, and a new desirable property called adversarial robustness essential to trust operations based on ML outputs. Most work in AML is built upon a game-theoretic modeling of the conflict between a learning system and an adversary, ready to manipulate input data. This assumes that each agent knows their opponent’s interests and uncertainty judgments, facilitating inferences based on Nash equilibria. However, such common knowledge assumption is not realistic in the security scenarios typical of AML. After reviewing such game-theoretic approaches, we discuss the benefits that Bayesian perspectives provide when defending ML-based systems. We demonstrate how the Bayesian approach allows us to explicitly model our uncertainty about the opponent’s beliefs and interests, relaxing unrealistic assumptions, and providing more robust inferences. We illustrate this approach in supervised learning settings, and identify relevant future research problems. Supplementary materials for this article are available online., The authors acknowledge the support of the National Science Foundation under Grant DMS-1638521 to the Statistical and Applied Mathematical Science Institute (SAMSI),NC, USA. RN acknowledges the support of CUNEF University. DRI is supported by the AXA-ICMAT Chair and the Spanish Ministry of Science program PID2021-124662OB-I00. VG acknowledges support from grant FPU16-05034. This work is supported by the Severo Ochoa Excellence Programme CEX-2019-000904-S, the European Union’s Horizon 2020 Research and Innovation Programme under Grant Agreement No. 101021797 (Starlight) and 815003 (Trustonomy), the US NSF grant DMS-1638521 and a grants from the FBBVA (Amalfi), EOARD (FA8655-21-1-7042) and AFOSR (FA-9550-21- 1-0239)., With funding from the Spanish government through the "Severo Ochoa Centre of Excellence" accreditation (CEX2019-000904-S)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Unlocking the puzzle: non-defining mutations in SARS-CoV-2 proteome may affect vaccine effectiveness

  • Ulzurrun, Eugenia
  • Grande-Pérez, Ana
  • Del Hoyo, Daniel
  • Guevara, César Byron
  • Gil, Carmen
  • Sorzano, Carlos Óscar S.
  • Campillo, Nuria E.
14 p.-4 fig.-9 tab., Introduction: SARS-CoV-2 variants are defined by specific genome-wide mutations compared to the Wuhan genome. However, non-clade-defining mutations may also impact protein structure and function, potentially leading to reduced vaccine effectiveness. Our objective is to identify mutations across the entire viral genome rather than focus on individual mutations that may be associated with vaccine failure and to examine the physicochemical properties of the resulting amino acid changes., Materials and methods: Whole-genome consensus sequences of SARS-CoV-2 from COVID-19 patients were retrieved from the GISAID database. Analysis focused on Dataset_1 (7,154 genomes from Italy) and Dataset_2 (8,819 sequences from Spain). Bioinformatic tools identified amino acid changes resulting from codon mutations with frequencies of 10% or higher, and sequences were organized into sets based on identical amino acid combinations., Results: Non-defining mutations in SARS-CoV-2 genomes belonging to clades 21 L (Omicron), 22B/22E (Omicron), 22F/23A (Omicron) and 21J (Delta) were associated with vaccine failure. Four sets of sequences from Dataset_1 were significantly linked to low vaccine coverage: one from clade 21L with mutations L3201F (ORF1a), A27- (S) and G30- (N); two sets shared by clades 22B and 22E with changes A27- (S), I68- (S), R346T (S) and G30- (N); and one set shared by clades 22F and 23A containing changes A27- (S), F486P (S) and G30- (N). Booster doses showed a slight improvement in protection against Omicron clades. Regarding 21J (Delta) two sets of sequences from Dataset_2 exhibited the combination of non-clade mutations P2046L (ORF1a), P2287S (ORF1a), L829I (ORF1b), T95I (S), Y145H (S), R158- (S) and Q9L (N), that was associated with vaccine failure., Discussion: Vaccine coverage associations appear to be influenced by the mutations harbored by marketed vaccines. An analysis of the physicochemical properties of amino acid revealed that primarily hydrophobic and polar amino acid substitutions occurred. Our results suggest that non-defining mutations across the proteome of SARS-CoV-2 variants could affect the extent of protection of the COVID-19 vaccine. In addition, alteration of the physicochemical characteristics of viral amino acids could potentially disrupt protein structure or function or both., This research work was supported by the European Commission–NextGenerationEU (Regulation EU 2020/2094), through CSIC’s Global Health Platform (PTI Salud Global). Project: PID2021-124662OB-I00 financed by MCIN/AEI/10.13039/501100011033/and by FEDER “A way to make Europe.” With support from the AXA-ICMAT Chair in Adversarial Risk Analysis. The research was also made possible through the Proyectos Estratégicos Orientados a la Transición Ecológica y a la Transición Digital under the code “TED2021-129970B-C21.” AG-P acknowledges funding by the Programa Operativo FEDER 2014–2020 and Consejería de Economía y Conocimiento, Junta de Andalucía (grant number CV20-10932)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A cybersecurity risk analysis framework for systems with artificial intelligence components

  • Camacho Sosa-Días, Jorge
  • Couce-Vieira, A.
  • Arroyo Guardeño, David
  • Ríos Insua, David
28 páginas, 6 figuras, 9 tablas, The introduction of the European Union Artificial Intelligence (AI) Act, the NIST AI Risk Management Framework, and related international norms and policy documents demand a better understanding and implementation of novel risk analysis issues when facing systems with AI components: dealing with new AI- related impacts; incorporating AI-based assets within the cyber architecture; considering AI-based security and recovery controls within the cybersecurity portfolio; and managing novel AI-based targeted attacks. This paper suggests solutions to such issues and integrates them within a broad novel framework to support risk analysis in systems with AI components and services. An example concerning automated driving systems illustrates the framework validating it conceptually., The work was supported by the AXA-ICMAT Chair in Adversarial Risk Analysis, the EU’s Horizon 2020 Research and Innovation Programme under Grant Agreement No. 101021797 (STARLIGHT), the Spanish Ministry of Science program PID2021-124662OB-I00, AFOSR Eu- ropean Office of Aerospace Research and Development award FA8655-21-1-7042, a fellowship from “la Caixa” Foundation (ID 100010434), LCF/BQ/DI21/11860063, and grant PLEC2021- 007681 funded by MCIN/AEI/ 10.13039/501100011033, and by European Union NextGenera- tion EU/PRTR, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

WIDISBOT: Widget to analyse disinformation and content spread by bots.

  • Camacho, José Manuel
  • Pérez Miguel, Luis
  • Arroyo Guardeño, David
6 páginas, 3 figuras, The increasing prevalence of bots poses a sig- nificant challenge for maintaining the integrity of online information. Bot campaigns have been deployed for both economic scams and political interference, making it necessary to develop a system to detect these agents and ana- lyze their behavior. We present a scalable appli- cation designed to identify bots and to buttress the investigation of disinformation campaigns. Our intention is to provide professionals with- out technical expertise with an effective tool to identify and analyze content generated by bots. This will enable researchers from diverse backgrounds to study bot activity, fostering an interdisciplinary understanding of the strategies these agents use to spread disinformation, and the characteristics of their discourse. We illus- trate how to use the application through a case study on COVID-19., This work was supported by the Spanish Ministry of Science program PID2021-124662OB-I00; a fellowship from ”la Caixa” Foundation (ID 100010434), whose code is LCF/BQ/ DI21/11860063; and Grant PLEC2021-007681 (project XAI-DisInfodemics) funded by MCIN/AEI/ 10.13039/501100011033 and by European Union NextGeneration EU/PRTR; and BBVA Foundation project AMALFI., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

WIDISBOT. Widget to analyze disinformation and content spread by bots.

  • Camacho, José Manuel
  • Pérez Miguel, Luis
  • Arroyo Guardeño, David
Proceedings of the 4th Conference on Language, Data and Knowledge, 12 september 2023, Vienna, Austria. 6 páginas, 3 figuras, 1 tabla, The increasing prevalence of bots poses a sig- nificant challenge for maintaining the integrity of online information. Bot campaigns have been deployed for both economic scams and political interference, making it necessary to develop a system to detect these agents and ana- lyze their behavior. We present a scalable appli- cation designed to identify bots and to buttress the investigation of disinformation campaigns. Our intention is to provide professionals with- out technical expertise with an effective tool to identify and analyze content generated by bots. This will enable researchers from diverse backgrounds to study bot activity, fostering an interdisciplinary understanding of the strategies these agents use to spread disinformation, and the characteristics of their discourse. We illus- trate how to use the application through a case study on COVID-19., This work was supported by the Spanish Ministry of Science program PID2021-124662OB-I00; a fellowship from ”la Caixa” Foundation (ID 100010434), whose code is LCF/BQ/ DI21/11860063; and Grant PLEC2021-007681 (project XAI-DisInfodemics) funded by MCIN/AEI/ 10.13039/501100011033 and by European Union NextGeneration EU/PRTR; and BBVA Foundation project AMALFI., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Machine learning approaches to dietary classification from dental microtexture in primates

  • Estebaranz-Sánchez, Ferran
  • Kit, Kristina
  • Ibáñez Estevez, Juan José
  • Insua, David R.
  • Rodríguez Santana, Simón
  • Martínez, Laura M.
Dental microwear texture (DMT) analysis is a critical proxy for reconstructing the diets of extant and extinct mammals. While craniodental morphology reflects selective pressures across evolutionary timescales, microwear captures localized, short-term dietary signals over weeks to months. However, the high dimensionality of modern 3D surface microtexture data, often spanning disparate parameter sets (such as ISO standards and scale-sensitive fractal analysis, SSFA), complicates classification, particularly when working with limited paleontological datasets. To address this, we present a robust machine learning pipeline designed to automatically classify primate samples () across 6 dietary groups and 7 species. Our methodology leverages a nested leave-one-out cross-validation framework to evaluate multiple classifiers, including multinomial logistic regression (MLR) with various regularization approaches, Naive Bayes, and tree-based ensemble algorithms (e.g., Random forests, XGBoost). Our results demonstrate that Lasso-regularized MLR and Naive Bayes yield the highest predictive performance while enforcing strict feature selection to maintain interpretability. Crucially, models relying exclusively on ISO parameters consistently outperformed those using SSFA, as ISO variables better capture the microroughness localized mechanical abrasions generated by specific diets in our dataset. Furthermore, the integration of novel Fourier-based descriptors and isotropy variables significantly enhanced models’ discriminating power. By providing a mathematically rigorous framework to isolate precise ecological signals from noisy, high-dimensional data, this approach enables more accurate and reproducible dietary classifications. Ultimately, refining these dietary reconstructions is essential for resolving broader questions regarding niche partitioning, species evolution, and paleoecological dynamics.