Adversarial image generation using genetic algorithms with black-box technique

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 o...

Descripción completa

Detalles Bibliográficos
Autores principales: Pérez, Gabriela Alejandra, Pons, Claudia Fabiana
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2023
Materias:
Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/165930
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-165930
record_format dspace
spelling I19-R120-10915-1659302024-05-10T20:04:57Z http://sedici.unlp.edu.ar/handle/10915/165930 Adversarial image generation using genetic algorithms with black-box technique Pérez, Gabriela Alejandra Pons, Claudia Fabiana 2023-09 2023 2024-05-10T18:47:52Z en Ciencias Informáticas Convolutional Neural Networks Adversarial Images Genetic Algorithms 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 Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 82-94
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
spellingShingle Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
Pérez, Gabriela Alejandra
Pons, Claudia Fabiana
Adversarial image generation using genetic algorithms with black-box technique
topic_facet Ciencias Informáticas
Convolutional Neural Networks
Adversarial Images
Genetic Algorithms
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.
format Objeto de conferencia
Objeto de conferencia
author Pérez, Gabriela Alejandra
Pons, Claudia Fabiana
author_facet Pérez, Gabriela Alejandra
Pons, Claudia Fabiana
author_sort Pérez, Gabriela Alejandra
title Adversarial image generation using genetic algorithms with black-box technique
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
publishDate 2023
url http://sedici.unlp.edu.ar/handle/10915/165930
work_keys_str_mv AT perezgabrielaalejandra adversarialimagegenerationusinggeneticalgorithmswithblackboxtechnique
AT ponsclaudiafabiana adversarialimagegenerationusinggeneticalgorithmswithblackboxtechnique
_version_ 1807223107123937280

Ejemplares similares