Mostrar el registro sencillo del ítem

dc.contributor.authorRodríguez Rodríguez, José Antonio
dc.contributor.authorPérez Bravo, José María
dc.contributor.authorGarcía-González, Jorge
dc.contributor.authorMolina-Cabello, Miguel Ángel 
dc.contributor.authorThurnhofer-Hemsi, Karl
dc.contributor.authorLópez-Rubio, Ezequiel 
dc.date.accessioned2022-06-16T10:08:27Z
dc.date.available2022-06-16T10:08:27Z
dc.date.created2022-06-16
dc.date.issued2022
dc.identifier.urihttps://hdl.handle.net/10630/24396
dc.description.abstractImage classification has undergone a revolution in recent years due to the high performance of new deep learning models. However, severe security issues may impact the performance of these systems. In particular, adversarial attacks are based on modifying input images in a way that is imperceptible for human vision, so that deep learning image classifiers are deceived. This work proposes a new deep neural network model composed of an encoder and a Generative Adversarial Network (GAN). The former encodes a possibly malformed input image into a latent vector, while the latter generates a reconstructed image from the latent vector. Then the reconstructed image can be reliably classified because our model removes the deleterious effects of the attack. The experiments carried out were designed to test the proposed approach against the Fast Gradient Signed Method attack. The obtained results demonstrate the suitability of our approach in terms of an excellent balance between classification accuracy and computational cost.es_ES
dc.description.sponsorshipUniversidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.es_ES
dc.language.isoenges_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.subjectInteligencia artificiales_ES
dc.subjectAlgoritmoses_ES
dc.subjectRedes neuronales (Informática)es_ES
dc.subjectAprendizaje automático (Inteligencia artificial)es_ES
dc.subject.otherAdversarial attackes_ES
dc.subject.otherGenerative adversarial networkses_ES
dc.subject.otherFast gradient signed method attackes_ES
dc.titleEncoding generative adversarial networks for defense against image classification attackses_ES
dc.typeinfo:eu-repo/semantics/conferenceObjectes_ES
dc.centroE.T.S.I. Informáticaes_ES
dc.relation.eventtitleInternational Work-Conference on the Interplay Between Natural and Artificial Computation (IWINAC 2022)es_ES
dc.relation.eventplacePuerto de la Cruz (Tenerife), Españaes_ES
dc.relation.eventdateMayo de 2022es_ES


Ficheros en el ítem

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem