Detection of adversarial examples through chaos quantification in time-series analysis

In the realm of deep learning, deep neural networks (DNNs) have recently propelled significant advancements in image classification applications. However, these DNN models are vulnerable to adversarial examples (AE), which are crafted by introducing imperceptible perturbations to legitimate samples,...

Descripción completa

Detalles Bibliográficos
Autores: Singh, Harbinder, Pedraza Dorado, Aníbal, Déniz Suárez, Óscar, Bueno García, María Gloria
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Fundación Dialnet. Universidad de La Rioja
Repositorio:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:ruidera.uclm.es:10578/45780
Acceso en línea:https://doi.org/10.1007/s13042-025-02702-0
https://hdl.handle.net/10578/45780
https://link.springer.com/article/10.1007/s13042-025-02702-0
Access Level:acceso abierto
Palabra clave:Adversarial examples
Attacks
Chaos theory
Classifier
Guided filter
Space filling curves
id ES_87c810f55ce5cd092ceacddc79d057a2
oai_identifier_str oai:ruidera.uclm.es:10578/45780
network_acronym_str ES
network_name_str España
repository_id_str
spelling Detection of adversarial examples through chaos quantification in time-series analysisSingh, HarbinderPedraza Dorado, AníbalDéniz Suárez, ÓscarBueno García, María GloriaAdversarial examplesAttacksChaos theoryClassifierGuided filterSpace filling curvesIn the realm of deep learning, deep neural networks (DNNs) have recently propelled significant advancements in image classification applications. However, these DNN models are vulnerable to adversarial examples (AE), which are crafted by introducing imperceptible perturbations to legitimate samples, leading the models to make incorrect predictions. Time-series (TS) data are prevalent in real-world applications and naturally occurring phenomena. To recover and infer missing information, TS analysis has been extensively explored as a foundational research problem. The introduction of imperceptible perturbations induces irregularities in TS, resulting in chaotic behavior. Chaos, marked by a lack of organization and structure, is expected to play diverse functional roles in dynamical systems when analyzed through TS. By applying chaos theory to TS analysis, we aim to identify chaotic behavior to detect the subtle input perturbations added by the adversarial attacks. Chaos theory faces significant challenges when applied to the analysis or computation of chaotic systems due to the minimal and subtle nature of the perturbations introduced by adversarial attacks. Nonetheless, detecting chaos amidst adversarial perturbations is crucial for defending against such attacks. In this paper, we utilize features derived from ordinal patterns (OP) through TS analysis to detect the presence or absence of chaos, even under sophisticated attack methods. As an initial application of our pipeline, we exploit the edge-preserving capabilities of the guided filter (GF) and the spatial proximity properties of the Hilbert space-filling curve (HSFC) to represent the TS of input images. Experimental results show that our proposed method effectively identifies adversarial perturbations across various attacks on diverse datasets, including MNIST, Fashion-MNIST (FMNIST), CIFAR-10 and CIFAR-100.Springer202520252025info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://doi.org/10.1007/s13042-025-02702-0https://hdl.handle.net/10578/45780https://link.springer.com/article/10.1007/s13042-025-02702-0reponame:RUIdeRA. Repositorio Institucional de la UCLMinstname:Fundación Dialnet. Universidad de La RiojaInglésdAIEdge Grant n.º 101120726SBPLY/21/180501/000025info:eu-repo/semantics/openAccessoai:ruidera.uclm.es:10578/457802026-05-27T07:36:41Z
dc.title.none.fl_str_mv Detection of adversarial examples through chaos quantification in time-series analysis
title Detection of adversarial examples through chaos quantification in time-series analysis
spellingShingle Detection of adversarial examples through chaos quantification in time-series analysis
Singh, Harbinder
Adversarial examples
Attacks
Chaos theory
Classifier
Guided filter
Space filling curves
title_short Detection of adversarial examples through chaos quantification in time-series analysis
title_full Detection of adversarial examples through chaos quantification in time-series analysis
title_fullStr Detection of adversarial examples through chaos quantification in time-series analysis
title_full_unstemmed Detection of adversarial examples through chaos quantification in time-series analysis
title_sort Detection of adversarial examples through chaos quantification in time-series analysis
dc.creator.none.fl_str_mv Singh, Harbinder
Pedraza Dorado, Aníbal
Déniz Suárez, Óscar
Bueno García, María Gloria
author Singh, Harbinder
author_facet Singh, Harbinder
Pedraza Dorado, Aníbal
Déniz Suárez, Óscar
Bueno García, María Gloria
author_role author
author2 Pedraza Dorado, Aníbal
Déniz Suárez, Óscar
Bueno García, María Gloria
author2_role author
author
author
dc.subject.none.fl_str_mv Adversarial examples
Attacks
Chaos theory
Classifier
Guided filter
Space filling curves
topic Adversarial examples
Attacks
Chaos theory
Classifier
Guided filter
Space filling curves
description In the realm of deep learning, deep neural networks (DNNs) have recently propelled significant advancements in image classification applications. However, these DNN models are vulnerable to adversarial examples (AE), which are crafted by introducing imperceptible perturbations to legitimate samples, leading the models to make incorrect predictions. Time-series (TS) data are prevalent in real-world applications and naturally occurring phenomena. To recover and infer missing information, TS analysis has been extensively explored as a foundational research problem. The introduction of imperceptible perturbations induces irregularities in TS, resulting in chaotic behavior. Chaos, marked by a lack of organization and structure, is expected to play diverse functional roles in dynamical systems when analyzed through TS. By applying chaos theory to TS analysis, we aim to identify chaotic behavior to detect the subtle input perturbations added by the adversarial attacks. Chaos theory faces significant challenges when applied to the analysis or computation of chaotic systems due to the minimal and subtle nature of the perturbations introduced by adversarial attacks. Nonetheless, detecting chaos amidst adversarial perturbations is crucial for defending against such attacks. In this paper, we utilize features derived from ordinal patterns (OP) through TS analysis to detect the presence or absence of chaos, even under sophisticated attack methods. As an initial application of our pipeline, we exploit the edge-preserving capabilities of the guided filter (GF) and the spatial proximity properties of the Hilbert space-filling curve (HSFC) to represent the TS of input images. Experimental results show that our proposed method effectively identifies adversarial perturbations across various attacks on diverse datasets, including MNIST, Fashion-MNIST (FMNIST), CIFAR-10 and CIFAR-100.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://doi.org/10.1007/s13042-025-02702-0
https://hdl.handle.net/10578/45780
https://link.springer.com/article/10.1007/s13042-025-02702-0
url https://doi.org/10.1007/s13042-025-02702-0
https://hdl.handle.net/10578/45780
https://link.springer.com/article/10.1007/s13042-025-02702-0
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv dAIEdge Grant n.º 101120726
SBPLY/21/180501/000025
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:RUIdeRA. Repositorio Institucional de la UCLM
instname:Fundación Dialnet. Universidad de La Rioja
instname_str Fundación Dialnet. Universidad de La Rioja
reponame_str RUIdeRA. Repositorio Institucional de la UCLM
collection RUIdeRA. Repositorio Institucional de la UCLM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412487543128064
score 15,811543

Similares en LA Referencia