A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach

Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean da...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Mohammed Nasser Al-Andoli [verfasserIn] Shing Chiang Tan [verfasserIn] Kok Swee Sim [verfasserIn] Pey Yun Goh [verfasserIn] Chee Peng Lim [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2024

Schlagwörter:	Deep learning adversarial examples security adversarial attacks adversarial examples detection

Übergeordnetes Werk:	In: IEEE Access - IEEE, 2014, 12(2024), Seite 17522-17540
Übergeordnetes Werk:	volume:12 ; year:2024 ; pages:17522-17540

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.1109/ACCESS.2024.3354699

Katalog-ID:	DOAJ094858667

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ094858667
003	DE-627
005	20240413081505.0
007	cr uuu---uuuuu
008	240413s2024 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1109/ACCESS.2024.3354699 \|2 doi
035			\|a (DE-627)DOAJ094858667
035			\|a (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a TK1-9971
100	0		\|a Mohammed Nasser Al-Andoli \|e verfasserin \|4 aut
245	1	2	\|a A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
264		1	\|c 2024
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.
650		4	\|a Deep learning
650		4	\|a adversarial examples
650		4	\|a security
650		4	\|a adversarial attacks
650		4	\|a adversarial examples detection
653		0	\|a Electrical engineering. Electronics. Nuclear engineering
700	0		\|a Shing Chiang Tan \|e verfasserin \|4 aut
700	0		\|a Kok Swee Sim \|e verfasserin \|4 aut
700	0		\|a Pey Yun Goh \|e verfasserin \|4 aut
700	0		\|a Chee Peng Lim \|e verfasserin \|4 aut
773	0	8	\|i In \|t IEEE Access \|d IEEE, 2014 \|g 12(2024), Seite 17522-17540 \|w (DE-627)728440385 \|w (DE-600)2687964-5 \|x 21693536 \|7 nnns
773	1	8	\|g volume:12 \|g year:2024 \|g pages:17522-17540
856	4	0	\|u https://doi.org/10.1109/ACCESS.2024.3354699 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 \|z kostenfrei
856	4	0	\|u https://ieeexplore.ieee.org/document/10400453/ \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2169-3536 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 12 \|j 2024 \|h 17522-17540

Indexfelder

author_variant	m n a a mnaa s c t sct k s s kss p y g pyg c p l cpl
matchkey_str	article:21693536:2024----::faeokorbsdelannmdlaantdesraatcsaeo
hierarchy_sort_str	2024
callnumber-subject-code	TK
publishDate	2024
allfields	10.1109/ACCESS.2024.3354699 doi (DE-627)DOAJ094858667 (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586 DE-627 ger DE-627 rakwb eng TK1-9971 Mohammed Nasser Al-Andoli verfasserin aut A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs. Deep learning adversarial examples security adversarial attacks adversarial examples detection Electrical engineering. Electronics. Nuclear engineering Shing Chiang Tan verfasserin aut Kok Swee Sim verfasserin aut Pey Yun Goh verfasserin aut Chee Peng Lim verfasserin aut In IEEE Access IEEE, 2014 12(2024), Seite 17522-17540 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:12 year:2024 pages:17522-17540 https://doi.org/10.1109/ACCESS.2024.3354699 kostenfrei https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 kostenfrei https://ieeexplore.ieee.org/document/10400453/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 12 2024 17522-17540
spelling	10.1109/ACCESS.2024.3354699 doi (DE-627)DOAJ094858667 (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586 DE-627 ger DE-627 rakwb eng TK1-9971 Mohammed Nasser Al-Andoli verfasserin aut A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs. Deep learning adversarial examples security adversarial attacks adversarial examples detection Electrical engineering. Electronics. Nuclear engineering Shing Chiang Tan verfasserin aut Kok Swee Sim verfasserin aut Pey Yun Goh verfasserin aut Chee Peng Lim verfasserin aut In IEEE Access IEEE, 2014 12(2024), Seite 17522-17540 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:12 year:2024 pages:17522-17540 https://doi.org/10.1109/ACCESS.2024.3354699 kostenfrei https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 kostenfrei https://ieeexplore.ieee.org/document/10400453/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 12 2024 17522-17540
allfields_unstemmed	10.1109/ACCESS.2024.3354699 doi (DE-627)DOAJ094858667 (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586 DE-627 ger DE-627 rakwb eng TK1-9971 Mohammed Nasser Al-Andoli verfasserin aut A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs. Deep learning adversarial examples security adversarial attacks adversarial examples detection Electrical engineering. Electronics. Nuclear engineering Shing Chiang Tan verfasserin aut Kok Swee Sim verfasserin aut Pey Yun Goh verfasserin aut Chee Peng Lim verfasserin aut In IEEE Access IEEE, 2014 12(2024), Seite 17522-17540 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:12 year:2024 pages:17522-17540 https://doi.org/10.1109/ACCESS.2024.3354699 kostenfrei https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 kostenfrei https://ieeexplore.ieee.org/document/10400453/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 12 2024 17522-17540
allfieldsGer	10.1109/ACCESS.2024.3354699 doi (DE-627)DOAJ094858667 (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586 DE-627 ger DE-627 rakwb eng TK1-9971 Mohammed Nasser Al-Andoli verfasserin aut A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs. Deep learning adversarial examples security adversarial attacks adversarial examples detection Electrical engineering. Electronics. Nuclear engineering Shing Chiang Tan verfasserin aut Kok Swee Sim verfasserin aut Pey Yun Goh verfasserin aut Chee Peng Lim verfasserin aut In IEEE Access IEEE, 2014 12(2024), Seite 17522-17540 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:12 year:2024 pages:17522-17540 https://doi.org/10.1109/ACCESS.2024.3354699 kostenfrei https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 kostenfrei https://ieeexplore.ieee.org/document/10400453/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 12 2024 17522-17540
allfieldsSound	10.1109/ACCESS.2024.3354699 doi (DE-627)DOAJ094858667 (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586 DE-627 ger DE-627 rakwb eng TK1-9971 Mohammed Nasser Al-Andoli verfasserin aut A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach 2024 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs. Deep learning adversarial examples security adversarial attacks adversarial examples detection Electrical engineering. Electronics. Nuclear engineering Shing Chiang Tan verfasserin aut Kok Swee Sim verfasserin aut Pey Yun Goh verfasserin aut Chee Peng Lim verfasserin aut In IEEE Access IEEE, 2014 12(2024), Seite 17522-17540 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:12 year:2024 pages:17522-17540 https://doi.org/10.1109/ACCESS.2024.3354699 kostenfrei https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 kostenfrei https://ieeexplore.ieee.org/document/10400453/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 12 2024 17522-17540
language	English
source	In IEEE Access 12(2024), Seite 17522-17540 volume:12 year:2024 pages:17522-17540
sourceStr	In IEEE Access 12(2024), Seite 17522-17540 volume:12 year:2024 pages:17522-17540
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	Deep learning adversarial examples security adversarial attacks adversarial examples detection Electrical engineering. Electronics. Nuclear engineering
isfreeaccess_bool	true
container_title	IEEE Access
authorswithroles_txt_mv	Mohammed Nasser Al-Andoli @@aut@@ Shing Chiang Tan @@aut@@ Kok Swee Sim @@aut@@ Pey Yun Goh @@aut@@ Chee Peng Lim @@aut@@
publishDateDaySort_date	2024-01-01T00:00:00Z
hierarchy_top_id	728440385
id	DOAJ094858667
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ094858667</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413081505.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240413s2024 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/ACCESS.2024.3354699</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ094858667</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJb5e4057a3373471aa42f4cdc86757586</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TK1-9971</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Mohammed Nasser Al-Andoli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2024</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">adversarial examples</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">security</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">adversarial attacks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">adversarial examples detection</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electrical engineering. Electronics. Nuclear engineering</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Shing Chiang Tan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kok Swee Sim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Pey Yun Goh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chee Peng Lim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">IEEE Access</subfield><subfield code="d">IEEE, 2014</subfield><subfield code="g">12(2024), Seite 17522-17540</subfield><subfield code="w">(DE-627)728440385</subfield><subfield code="w">(DE-600)2687964-5</subfield><subfield code="x">21693536</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:12</subfield><subfield code="g">year:2024</subfield><subfield code="g">pages:17522-17540</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1109/ACCESS.2024.3354699</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://ieeexplore.ieee.org/document/10400453/</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2169-3536</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">12</subfield><subfield code="j">2024</subfield><subfield code="h">17522-17540</subfield></datafield></record></collection>
callnumber-first	T - Technology
author	Mohammed Nasser Al-Andoli
spellingShingle	Mohammed Nasser Al-Andoli misc TK1-9971 misc Deep learning misc adversarial examples misc security misc adversarial attacks misc adversarial examples detection misc Electrical engineering. Electronics. Nuclear engineering A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
authorStr	Mohammed Nasser Al-Andoli
ppnlink_with_tag_str_mv	@@773@@(DE-627)728440385
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	TK1-9971
illustrated	Not Illustrated
issn	21693536
topic_title	TK1-9971 A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach Deep learning adversarial examples security adversarial attacks adversarial examples detection
topic	misc TK1-9971 misc Deep learning misc adversarial examples misc security misc adversarial attacks misc adversarial examples detection misc Electrical engineering. Electronics. Nuclear engineering
topic_unstemmed	misc TK1-9971 misc Deep learning misc adversarial examples misc security misc adversarial attacks misc adversarial examples detection misc Electrical engineering. Electronics. Nuclear engineering
topic_browse	misc TK1-9971 misc Deep learning misc adversarial examples misc security misc adversarial attacks misc adversarial examples detection misc Electrical engineering. Electronics. Nuclear engineering
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	IEEE Access
hierarchy_parent_id	728440385
hierarchy_top_title	IEEE Access
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)728440385 (DE-600)2687964-5
title	A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
ctrlnum	(DE-627)DOAJ094858667 (DE-599)DOAJb5e4057a3373471aa42f4cdc86757586
title_full	A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
author_sort	Mohammed Nasser Al-Andoli
journal	IEEE Access
journalStr	IEEE Access
callnumber-first-code	T
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2024
contenttype_str_mv	txt
container_start_page	17522
author_browse	Mohammed Nasser Al-Andoli Shing Chiang Tan Kok Swee Sim Pey Yun Goh Chee Peng Lim
container_volume	12
class	TK1-9971
format_se	Elektronische Aufsätze
author-letter	Mohammed Nasser Al-Andoli
doi_str_mv	10.1109/ACCESS.2024.3354699
author2-role	verfasserin
title_sort	framework for robust deep learning models against adversarial attacks based on a protection layer approach
callnumber	TK1-9971
title_auth	A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
abstract	Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.
abstractGer	Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.
abstract_unstemmed	Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
title_short	A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
url	https://doi.org/10.1109/ACCESS.2024.3354699 https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586 https://ieeexplore.ieee.org/document/10400453/ https://doaj.org/toc/2169-3536
remote_bool	true
author2	Shing Chiang Tan Kok Swee Sim Pey Yun Goh Chee Peng Lim
author2Str	Shing Chiang Tan Kok Swee Sim Pey Yun Goh Chee Peng Lim
ppnlink	728440385
callnumber-subject	TK - Electrical and Nuclear Engineering
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.1109/ACCESS.2024.3354699
callnumber-a	TK1-9971
up_date	2024-07-04T00:57:34.444Z
_version_	1803608029342466048
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ094858667</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413081505.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240413s2024 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/ACCESS.2024.3354699</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ094858667</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJb5e4057a3373471aa42f4cdc86757586</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TK1-9971</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Mohammed Nasser Al-Andoli</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2024</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">adversarial examples</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">security</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">adversarial attacks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">adversarial examples detection</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electrical engineering. Electronics. Nuclear engineering</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Shing Chiang Tan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Kok Swee Sim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Pey Yun Goh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Chee Peng Lim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">IEEE Access</subfield><subfield code="d">IEEE, 2014</subfield><subfield code="g">12(2024), Seite 17522-17540</subfield><subfield code="w">(DE-627)728440385</subfield><subfield code="w">(DE-600)2687964-5</subfield><subfield code="x">21693536</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:12</subfield><subfield code="g">year:2024</subfield><subfield code="g">pages:17522-17540</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1109/ACCESS.2024.3354699</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/b5e4057a3373471aa42f4cdc86757586</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://ieeexplore.ieee.org/document/10400453/</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2169-3536</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">12</subfield><subfield code="j">2024</subfield><subfield code="h">17522-17540</subfield></datafield></record></collection>
score	7.4021244

Nicht das Richtige dabei?

Schreiben Sie uns!

A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?