Adversarial image generation using genetic algorithms with black-box technique

Autores
Pérez, Gabriela Alejandra; Pons, Claudia Fabiana
Año de publicación
2023
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Convolutional neural networks are a technique that has demonstrated great success in computer vision tasks, such as image classification and object detection. Like any machine learning model, they have limitations and vulnerabilities that must be carefully considered for safeand effective use. One of the main limitations lies in their complexity and the difficulty of interpreting their internal workings, which can be exploited for malicious purposes. The goal of these attacks is to make deliberate changes to the input data in order to deceive the model and cause it to make incorrect decisions. These attacks are known as adversarial attacks. This work focuses on the generation of adversarial images using genetic  algorithms for a convolutional neural network trained on the MNIST dataset. Several strategies are employed, including targeted and untargeted attacks, as well as the presentation of interpretable and non-interpretable images that are unrecognizable to humans but are misidentified and confidently classified by the network. The experiment demonstrates the ability to generate adversarial images in a relatively short time, highlighting the vulnerability of neural networks and the ease with which they can be deceived. These results underscore the importance of developing more secure and reliable artificial intelligence systems capable of resisting such attacks.
Las redes neuronales convolucionales conforman una tecnica que ha demostrado un gran éxito en tareas de visión artificial, como laclasificación de imágenes y detección de objetos. Como cualquier modelo de aprendizaje automático, tiene limitaciones y vulnerabilidades quedeben ser consideradas cuidadosamente para utilizarlas de manera segura y efectiva. Una de las limitaciones principales se encuentra en sucomplejidad y la dificultad de interpretar su funcionamiento interno, lo que puede ser explotado con fines maliciosos. El objetivo de estos ataquesconsiste en hacer cambios deliberados en la entrada de datos, de forma tal de engañar al modelo y hacer que tome decisiones incorrectas. Estosataques son conocidos como ataques adversarios. Este trabajo se centra en la generación de imágenes adversarias utilizando algoritmos genéticos para una red neuronal convolucional entrenada con el dataset MNIST. Se utilizan varias estrategias incluyendo ataques dirigidos y no dirigidos, así como también se presentan imágenes interpretables y no interpretables, no reconocibles para los humanos, pero que la red identifica y clasifica erróneamente con alta confianza. El experimento muestra la posibilidad de generar imágenes adversarias en un tiempo relativamente corto, lo que pone en evidencia la vulnerabilidad de las redes neuronales y la facilidad con la que pueden ser engañadas. Estos resultados resaltan la importancia de desarrollar sistemas de inteligencia artificial más seguros y confiables, capaces de resistir estos ataques.
Sociedad Argentina de Informática e Investigación Operativa
Materia
Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/165930

id SEDICI_2a3bd8fa58bae613d98ebf2f05843ccc
oai_identifier_str oai:sedici.unlp.edu.ar:10915/165930
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Adversarial image generation using genetic algorithms with black-box techniquePérez, Gabriela AlejandraPons, Claudia FabianaCiencias InformáticasConvolutional Neural NetworksAdversarial ImagesGenetic AlgorithmsConvolutional neural networks are a technique that has demonstrated great success in computer vision tasks, such as image classification and object detection. Like any machine learning model, they have limitations and vulnerabilities that must be carefully considered for safeand effective use. One of the main limitations lies in their complexity and the difficulty of interpreting their internal workings, which can be exploited for malicious purposes. The goal of these attacks is to make deliberate changes to the input data in order to deceive the model and cause it to make incorrect decisions. These attacks are known as adversarial attacks. This work focuses on the generation of adversarial images using genetic  algorithms for a convolutional neural network trained on the MNIST dataset. Several strategies are employed, including targeted and untargeted attacks, as well as the presentation of interpretable and non-interpretable images that are unrecognizable to humans but are misidentified and confidently classified by the network. The experiment demonstrates the ability to generate adversarial images in a relatively short time, highlighting the vulnerability of neural networks and the ease with which they can be deceived. These results underscore the importance of developing more secure and reliable artificial intelligence systems capable of resisting such attacks.Las redes neuronales convolucionales conforman una tecnica que ha demostrado un gran éxito en tareas de visión artificial, como laclasificación de imágenes y detección de objetos. Como cualquier modelo de aprendizaje automático, tiene limitaciones y vulnerabilidades quedeben ser consideradas cuidadosamente para utilizarlas de manera segura y efectiva. Una de las limitaciones principales se encuentra en sucomplejidad y la dificultad de interpretar su funcionamiento interno, lo que puede ser explotado con fines maliciosos. El objetivo de estos ataquesconsiste en hacer cambios deliberados en la entrada de datos, de forma tal de engañar al modelo y hacer que tome decisiones incorrectas. Estosataques son conocidos como ataques adversarios. Este trabajo se centra en la generación de imágenes adversarias utilizando algoritmos genéticos para una red neuronal convolucional entrenada con el dataset MNIST. Se utilizan varias estrategias incluyendo ataques dirigidos y no dirigidos, así como también se presentan imágenes interpretables y no interpretables, no reconocibles para los humanos, pero que la red identifica y clasifica erróneamente con alta confianza. El experimento muestra la posibilidad de generar imágenes adversarias en un tiempo relativamente corto, lo que pone en evidencia la vulnerabilidad de las redes neuronales y la facilidad con la que pueden ser engañadas. Estos resultados resaltan la importancia de desarrollar sistemas de inteligencia artificial más seguros y confiables, capaces de resistir estos ataques.Sociedad Argentina de Informática e Investigación Operativa2023-09info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf82-94http://sedici.unlp.edu.ar/handle/10915/165930enginfo:eu-repo/semantics/altIdentifier/url/https://publicaciones.sadio.org.ar/index.php/JAIIO/article/view/670info:eu-repo/semantics/altIdentifier/issn/2451-7496info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-10-15T11:35:41Zoai:sedici.unlp.edu.ar:10915/165930Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-10-15 11:35:42.219SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Adversarial image generation using genetic algorithms with black-box technique
title Adversarial image generation using genetic algorithms with black-box technique
spellingShingle Adversarial image generation using genetic algorithms with black-box technique
Pérez, Gabriela Alejandra
Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
title_short Adversarial image generation using genetic algorithms with black-box technique
title_full Adversarial image generation using genetic algorithms with black-box technique
title_fullStr Adversarial image generation using genetic algorithms with black-box technique
title_full_unstemmed Adversarial image generation using genetic algorithms with black-box technique
title_sort Adversarial image generation using genetic algorithms with black-box technique
dc.creator.none.fl_str_mv Pérez, Gabriela Alejandra
Pons, Claudia Fabiana
author Pérez, Gabriela Alejandra
author_facet Pérez, Gabriela Alejandra
Pons, Claudia Fabiana
author_role author
author2 Pons, Claudia Fabiana
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
topic Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
dc.description.none.fl_txt_mv Convolutional neural networks are a technique that has demonstrated great success in computer vision tasks, such as image classification and object detection. Like any machine learning model, they have limitations and vulnerabilities that must be carefully considered for safeand effective use. One of the main limitations lies in their complexity and the difficulty of interpreting their internal workings, which can be exploited for malicious purposes. The goal of these attacks is to make deliberate changes to the input data in order to deceive the model and cause it to make incorrect decisions. These attacks are known as adversarial attacks. This work focuses on the generation of adversarial images using genetic  algorithms for a convolutional neural network trained on the MNIST dataset. Several strategies are employed, including targeted and untargeted attacks, as well as the presentation of interpretable and non-interpretable images that are unrecognizable to humans but are misidentified and confidently classified by the network. The experiment demonstrates the ability to generate adversarial images in a relatively short time, highlighting the vulnerability of neural networks and the ease with which they can be deceived. These results underscore the importance of developing more secure and reliable artificial intelligence systems capable of resisting such attacks.
Las redes neuronales convolucionales conforman una tecnica que ha demostrado un gran éxito en tareas de visión artificial, como laclasificación de imágenes y detección de objetos. Como cualquier modelo de aprendizaje automático, tiene limitaciones y vulnerabilidades quedeben ser consideradas cuidadosamente para utilizarlas de manera segura y efectiva. Una de las limitaciones principales se encuentra en sucomplejidad y la dificultad de interpretar su funcionamiento interno, lo que puede ser explotado con fines maliciosos. El objetivo de estos ataquesconsiste en hacer cambios deliberados en la entrada de datos, de forma tal de engañar al modelo y hacer que tome decisiones incorrectas. Estosataques son conocidos como ataques adversarios. Este trabajo se centra en la generación de imágenes adversarias utilizando algoritmos genéticos para una red neuronal convolucional entrenada con el dataset MNIST. Se utilizan varias estrategias incluyendo ataques dirigidos y no dirigidos, así como también se presentan imágenes interpretables y no interpretables, no reconocibles para los humanos, pero que la red identifica y clasifica erróneamente con alta confianza. El experimento muestra la posibilidad de generar imágenes adversarias en un tiempo relativamente corto, lo que pone en evidencia la vulnerabilidad de las redes neuronales y la facilidad con la que pueden ser engañadas. Estos resultados resaltan la importancia de desarrollar sistemas de inteligencia artificial más seguros y confiables, capaces de resistir estos ataques.
Sociedad Argentina de Informática e Investigación Operativa
description Convolutional neural networks are a technique that has demonstrated great success in computer vision tasks, such as image classification and object detection. Like any machine learning model, they have limitations and vulnerabilities that must be carefully considered for safeand effective use. One of the main limitations lies in their complexity and the difficulty of interpreting their internal workings, which can be exploited for malicious purposes. The goal of these attacks is to make deliberate changes to the input data in order to deceive the model and cause it to make incorrect decisions. These attacks are known as adversarial attacks. This work focuses on the generation of adversarial images using genetic  algorithms for a convolutional neural network trained on the MNIST dataset. Several strategies are employed, including targeted and untargeted attacks, as well as the presentation of interpretable and non-interpretable images that are unrecognizable to humans but are misidentified and confidently classified by the network. The experiment demonstrates the ability to generate adversarial images in a relatively short time, highlighting the vulnerability of neural networks and the ease with which they can be deceived. These results underscore the importance of developing more secure and reliable artificial intelligence systems capable of resisting such attacks.
publishDate 2023
dc.date.none.fl_str_mv 2023-09
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/165930
url http://sedici.unlp.edu.ar/handle/10915/165930
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://publicaciones.sadio.org.ar/index.php/JAIIO/article/view/670
info:eu-repo/semantics/altIdentifier/issn/2451-7496
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
82-94
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1846064381493772288
score 13.22299