Studying the Transferability of Non-Targeted Adversarial Attacks
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/138459
Título: | Studying the Transferability of Non-Targeted Adversarial Attacks |
---|---|
Autor/es: | Álvarez, Enrique | Alvarez, Rafael | Cazorla, Miguel |
Grupo/s de investigación o GITE: | Criptología y Seguridad Computacional | Robótica y Visión Tridimensional (RoViT) |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Palabras clave: | Deep Learning | Adversarial Attacks | Convolutional Neural Networks |
Fecha de publicación: | 22-sep-2021 |
Editor: | IEEE |
Cita bibliográfica: | E. Álvarez, R. Álvarez and M. Cazorla, "Studying the Transferability of Non-Targeted Adversarial Attacks," 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, 2021, pp. 1-6, doi: 10.1109/IJCNN52387.2021.9534138 |
Resumen: | There is no doubt that the use of machine learning is increasing every day. Its applications include self-driving cars, malware detection, recommendation systems and many other fields. Although the broad scope of this technology highlights the importance of its reliability, it has been shown that machine learning models can be vulnerable to adversarial attacks. In this paper, we study a property of these attacks called transferability across different architectures and models, measuring how these attacks transfer based on a specific number of parameters among three adversarial attacks: Fast Gradient Sign Method, Projected Gradient Descent and HopSkipJumpAttack. |
Patrocinador/es: | Experiments were made possible by a generous hardware donation from NVIDIA. Research partially supported by the Spanish Government under project grant RTI2018-097263-B-I00 (ACTIS). |
URI: | http://hdl.handle.net/10045/138459 |
ISBN: | 978-1-6654-3900-8 |
ISSN: | 2161-4407 |
DOI: | 10.1109/IJCNN52387.2021.9534138 |
Idioma: | spa |
Tipo: | info:eu-repo/semantics/conferenceObject |
Derechos: | © IEEE |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1109/IJCNN52387.2021.9534138 |
Aparece en las colecciones: | INV - CSC - Comunicaciones a Congresos, Conferencias, etc. INV - RoViT - Comunicaciones a Congresos, Conferencias, etc. |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Studying_the_Transferability_of_Non-Targeted_Adversarial_Attacks.pdf | Versión final (acceso restringido) | 1,11 MB | Adobe PDF | Abrir Solicitar una copia |
Studying_the_Transferability_of_Non-Targeted_Adversarial_Attacks-rev.pdf | Versión revisada (acceso abierto) | 2,78 MB | Adobe PDF | Abrir Vista previa |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.