dc.creator | Paluzo Hidalgo, Eduardo | es |
dc.creator | González Díaz, Rocío | es |
dc.creator | Gutiérrez Naranjo, Miguel Ángel | es |
dc.creator | Heras, Jónathan | es |
dc.date.accessioned | 2021-02-03T14:01:13Z | |
dc.date.available | 2021-02-03T14:01:13Z | |
dc.date.issued | 2021-01-15 | |
dc.identifier.citation | Paluzo Hidalgo, E., González Díaz, R., Gutiérrez Naranjo, M.Á. y Heras, J. (2021). Simplicial-Map Neural Networks Robust to Adversarial Examples. Mathematics, 9(2) (169), 1-1-16-16. | |
dc.identifier.issn | 2227-7390 (electrónico) | es |
dc.identifier.uri | https://hdl.handle.net/11441/104540 | |
dc.description.abstract | Broadly speaking, an adversarial example against a classification model occurs when a small perturbation on an input data point produces a change on the output label assigned by the model. Such adversarial examples represent a weakness for the safety of neural network applications, and many different solutions have been proposed for minimizing their effects. In this paper, we propose a new approach by means of a family of neural networks called simplicial-map neural networks constructed from an Algebraic Topology perspective. Our proposal is based on three main ideas. Firstly, given a classification problem, both the input dataset and its set of one-hot labels will be endowed with simplicial complex structures, and a simplicial map between such complexes will be defined. Secondly, a neural network characterizing the classification problem will be built from such a simplicial map. Finally, by considering barycentric subdivisions of the simplicial complexes, a decision boundary will be computed to make the neural network robust to adversarial attacks of a given size. | es |
dc.description.sponsorship | Ministerio de Ciencia, Innovación y Universidades (MICINN). España | es |
dc.description.sponsorship | FEDER/UE | es |
dc.format | application/pdf | es |
dc.format.extent | 16 p. | es |
dc.language.iso | eng | es |
dc.publisher | MDPI [Commercial Publisher] | es |
dc.relation.ispartof | Mathematics, 9(2) (169), 1-1-16-16. | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | algebraic topology | es |
dc.subject | neural network | es |
dc.subject | adversarial examples | es |
dc.title | Simplicial-Map Neural Networks Robust to Adversarial Examples | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Matemática Aplicada I | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Ciencias de la Computación e Inteligencia Artificial | es |
dc.relation.projectID | PID2019-107339GB-100 | es |
dc.relation.publisherversion | https://doi.org/10.3390/math9020169 | es |
dc.identifier.doi | 10.3390/math9020169 | es |
dc.journaltitle | Mathematics | es |
dc.publication.volumen | 9(2) | es |
dc.publication.issue | 169 | es |
dc.publication.initialPage | 1-1 | es |
dc.publication.endPage | 16-16 | es |
dc.contributor.funder | Ministerio de Ciencia, Innovación y Universidades (MICINN). España | es |
dc.contributor.funder | European Commission (EC). Fondo Europeo de Desarrollo Regional (FEDER) | es |