Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data

Machine learning is central to mainstream technology and outperforms classical approaches to handcrafted feature design. Aside from its learning process for artificial feature extraction, it has an end-to-end paradigm from input to output, reaching outstandingly accurate results. However, security c...

Full description

Saved in:
Bibliographic Details
Main Authors: Matthieu Olague, Gustavo Olague, Roberto Pineda, Gerardo Ibarra-Vazquez
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Data in Brief
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352340924010059
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850218865951244288
author Matthieu Olague
Gustavo Olague
Roberto Pineda
Gerardo Ibarra-Vazquez
author_facet Matthieu Olague
Gustavo Olague
Roberto Pineda
Gerardo Ibarra-Vazquez
author_sort Matthieu Olague
collection DOAJ
description Machine learning is central to mainstream technology and outperforms classical approaches to handcrafted feature design. Aside from its learning process for artificial feature extraction, it has an end-to-end paradigm from input to output, reaching outstandingly accurate results. However, security concerns about its robustness to malicious and imperceptible perturbations have drawn attention since humans or machines can change the predictions of programs entirely. Salient object detection is a research area where deep convolutional neural networks have proven effective but whose trustworthiness represents a significant issue requiring analysis and solutions to hackers' attacks. This dataset is an image repository containing five different image databases to evaluate adversarial robustness by introducing 12 adversarial examples, each leveraging a known adversarial attack or noise perturbation. The dataset comprises 56,387 digital images, resulting from applying adversarial examples on subsets of four standard databases (i.e., FT, PASCAL-S, ImgSal, DUTS) and a fifth database (SNPL) portraying a real-world visual attention problem of a shorebird called the snowy plover. We include original and rescaled images from the five databases used with the adversarial examples as part of this dataset for easy access and distribution.
format Article
id doaj-art-290c6acf0df04d39a3ea65aa40f9fc80
institution OA Journals
issn 2352-3409
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Data in Brief
spelling doaj-art-290c6acf0df04d39a3ea65aa40f9fc802025-08-20T02:07:34ZengElsevierData in Brief2352-34092024-12-015711104310.1016/j.dib.2024.111043Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley DataMatthieu Olague0Gustavo Olague1Roberto Pineda2Gerardo Ibarra-Vazquez3IBM Technology Campus Guadalajara, El Salto, 45680, MexicoDepartment of Computer Science, CICESE, Ensenada, 22860, México; Corresponding author.Department of Computer Science, CICESE, Ensenada, 22860, MéxicoDepartment of Data Science, ITESM, Monterrey, 64849, MéxicoMachine learning is central to mainstream technology and outperforms classical approaches to handcrafted feature design. Aside from its learning process for artificial feature extraction, it has an end-to-end paradigm from input to output, reaching outstandingly accurate results. However, security concerns about its robustness to malicious and imperceptible perturbations have drawn attention since humans or machines can change the predictions of programs entirely. Salient object detection is a research area where deep convolutional neural networks have proven effective but whose trustworthiness represents a significant issue requiring analysis and solutions to hackers' attacks. This dataset is an image repository containing five different image databases to evaluate adversarial robustness by introducing 12 adversarial examples, each leveraging a known adversarial attack or noise perturbation. The dataset comprises 56,387 digital images, resulting from applying adversarial examples on subsets of four standard databases (i.e., FT, PASCAL-S, ImgSal, DUTS) and a fifth database (SNPL) portraying a real-world visual attention problem of a shorebird called the snowy plover. We include original and rescaled images from the five databases used with the adversarial examples as part of this dataset for easy access and distribution.http://www.sciencedirect.com/science/article/pii/S2352340924010059Symbolic learningDeep learningVisual attentionAdversarial robustnessAdversarial examples
spellingShingle Matthieu Olague
Gustavo Olague
Roberto Pineda
Gerardo Ibarra-Vazquez
Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data
Data in Brief
Symbolic learning
Deep learning
Visual attention
Adversarial robustness
Adversarial examples
title Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data
title_full Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data
title_fullStr Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data
title_full_unstemmed Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data
title_short Salient object detection dataset with adversarial attacks for genetic programming and neural networksMendeley Data
title_sort salient object detection dataset with adversarial attacks for genetic programming and neural networksmendeley data
topic Symbolic learning
Deep learning
Visual attention
Adversarial robustness
Adversarial examples
url http://www.sciencedirect.com/science/article/pii/S2352340924010059
work_keys_str_mv AT matthieuolague salientobjectdetectiondatasetwithadversarialattacksforgeneticprogrammingandneuralnetworksmendeleydata
AT gustavoolague salientobjectdetectiondatasetwithadversarialattacksforgeneticprogrammingandneuralnetworksmendeleydata
AT robertopineda salientobjectdetectiondatasetwithadversarialattacksforgeneticprogrammingandneuralnetworksmendeleydata
AT gerardoibarravazquez salientobjectdetectiondatasetwithadversarialattacksforgeneticprogrammingandneuralnetworksmendeleydata