Exploring Transferability on Adversarial Attacks
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/137641
Title: | Exploring Transferability on Adversarial Attacks |
---|---|
Authors: | Álvarez, Enrique | Alvarez, Rafael | Cazorla, Miguel |
Research Group/s: | Robótica y Visión Tridimensional (RoViT) | Criptología y Seguridad Computacional |
Center, Department or Service: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Keywords: | Adversarial attacks | Convolutional neural networks | Deep learning | GeoDA | HopSkipJump | SurFree | Transferability |
Issue Date: | 26-Sep-2023 |
Publisher: | IEEE |
Citation: | IEEE Access. 2023, 11: 105545-105556. https://doi.org/10.1109/ACCESS.2023.3319389 |
Abstract: | In spite of the progress that has been made in the field, the problem of adversarial attacks remains unresolved. The most up-to-date models are still vulnerable, and there is not a simple way to defend against these kinds of attacks; even transformers can be affected by this problem, although they have not been extensively studied yet. In this paper, we study transferability, which is a property of adversarial attacks in which images generated for one architecture can be transferred to another and still be effective. In real-world scenarios like self-driving cars, malware detection, and face recognition authentication systems, transferability can lead to security issues. In order to conduct a behavioral analysis, we select a diverse set of networks and measure how effectively the images produced by various attacks can be transferred among them. We generate adversarial samples for each network and then evaluate them with other networks to determine the corresponding transferability performance. We can observe that all networks are susceptible to transferability attacks, albeit in some cases at the expense of severely distorted images. |
Sponsor: | This study has been funded by the ‘‘Methodology for EmotionAware Education Based on Artificial Intelligence’’ (Programa PROMETEO 2022—CIPROM/2021/017, Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital de la Generalitat Valenciana, Spain). |
URI: | http://hdl.handle.net/10045/137641 |
ISSN: | 2169-3536 |
DOI: | 10.1109/ACCESS.2023.3319389 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ |
Peer Review: | si |
Publisher version: | https://doi.org/10.1109/ACCESS.2023.3319389 |
Appears in Collections: | INV - CSC - Artículos de Revistas INV - RoViT - Artículos de Revistas |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Alvarez_etal_2023_IEEEAccess.pdf | 2,08 MB | Adobe PDF | Open Preview | |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.