Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain
In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving...
Gespeichert in:
| Veröffentlicht in: | PeerJ. Computer science 2021-04, Vol.7, p.e451-e451, Article 451 |
|---|---|
| Hauptverfasser: | , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | e451 |
|---|---|
| container_issue | |
| container_start_page | e451 |
| container_title | PeerJ. Computer science |
| container_volume | 7 |
| creator | Tabares-Soto, Reinel Brayan Arteaga-Arteaga, Harold Mora-Rubio, Alejandro Alejandro Bravo-Ortiz, Mario Arias-Garzon, Daniel Alzate Grisales, Jesus Alejandro Burbano Jacome, Alejandro Orozco-Arias, Simon Isaza, Gustavo Ramos Pollan, Raul |
| description | In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving steganographic images' detection accuracy, but it is unclear which computational elements are relevant. Here we present a strategy to improve accuracy, convergence, and stability during training. The strategy involves a preprocessing stage with Spatial Rich Models filters, Spatial Dropout, Absolute Value layer, and Batch Normalization. Using the strategy improves the performance of three steganalysis CNNs and two image classification CNNs by enhancing the accuracy from 2% up to 10% while reducing the training time to less than 6 h and improving the networks' stability. |
| doi_str_mv | 10.7717/peerj-cs.451 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_webof</sourceid><recordid>TN_cdi_gale_infotracmisc_A657879642</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A657879642</galeid><doaj_id>oai_doaj_org_article_ec5bda4e460a487d82b6b5e4a0df3391</doaj_id><sourcerecordid>A657879642</sourcerecordid><originalsourceid>FETCH-LOGICAL-c579t-f1ee4847ea637dea0803b7d47b87d45601cba13b374bd3d38f0f4c79923d6a903</originalsourceid><addsrcrecordid>eNqNks2O0zAUhSMEYkZldqxRJDYgaLHjxE42SKOKn0ojITGwthz7JuOSxsF2OvQVeGpu2qFMEQtiKbbs756bHJ8keUrJQggq3gwAfj3XYZEX9EFynjHB50VVZQ_vrc-SixDWhBBaUHyqx8kZY1WRZ4yfJz-vo1cR2l0aXWo3g3dbSOMNpErr0Su9S12TatdvXTdG63rVpT3gwTTFW-e_pcrrGxtBx9FDSNUwdBbMpGZsayOCdqNaSAM2UVi-Czaktt_3CIOKFgnjNsr2T5JHjeoCXNzNs-Tr-3dflh_nV58-rJaXV3NdiCrOGwqQl7kAxZkwoEhJWC1MLuoS3wUnVNeKspqJvDbMsLIhTa4FGsEMVxVhs2R10DVOreXg8fv8Tjpl5X7D-VYqH63uQIIuaqNyyDlROcqXWc3rAnJFTIMeUtR6e9AaxnoDRkOPdnYnoqcnvb2RrdvKkuQVzRgKvLgT8O77CCHKjQ0auk714MYgsyLLOC1EKRB9_he6dqNHSyeKoh7hBftDtQp_wPaNw756EpWXfNKpON78LFn8g8JhYGPxuqGxuH9S8PKkAJkIP2KrxhDk6vrzKfv6wGrvQvDQHP2gRE6xlfvYSh0kxhbxZ_c9PMK_Q4pAeQBuoXZN0BZ6DUcMg81ZleEgU8aXmLkpqEs39hFLX_1_KfsFkJwMJQ</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2510490653</pqid></control><display><type>article</type><title>Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain</title><source>DOAJ Directory of Open Access Journals</source><source>Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /></source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Tabares-Soto, Reinel ; Brayan Arteaga-Arteaga, Harold ; Mora-Rubio, Alejandro ; Alejandro Bravo-Ortiz, Mario ; Arias-Garzon, Daniel ; Alzate Grisales, Jesus Alejandro ; Burbano Jacome, Alejandro ; Orozco-Arias, Simon ; Isaza, Gustavo ; Ramos Pollan, Raul</creator><creatorcontrib>Tabares-Soto, Reinel ; Brayan Arteaga-Arteaga, Harold ; Mora-Rubio, Alejandro ; Alejandro Bravo-Ortiz, Mario ; Arias-Garzon, Daniel ; Alzate Grisales, Jesus Alejandro ; Burbano Jacome, Alejandro ; Orozco-Arias, Simon ; Isaza, Gustavo ; Ramos Pollan, Raul</creatorcontrib><description>In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving steganographic images' detection accuracy, but it is unclear which computational elements are relevant. Here we present a strategy to improve accuracy, convergence, and stability during training. The strategy involves a preprocessing stage with Spatial Rich Models filters, Spatial Dropout, Absolute Value layer, and Batch Normalization. Using the strategy improves the performance of three steganalysis CNNs and two image classification CNNs by enhancing the accuracy from 2% up to 10% while reducing the training time to less than 6 h and improving the networks' stability.</description><identifier>ISSN: 2376-5992</identifier><identifier>EISSN: 2376-5992</identifier><identifier>DOI: 10.7717/peerj-cs.451</identifier><identifier>PMID: 33954236</identifier><language>eng</language><publisher>LONDON: Peerj Inc</publisher><subject>Accuracy ; Algorithms ; Analysis ; Artificial Intelligence ; Artificial neural networks ; Cable television broadcasting industry ; Classification ; Computer architecture ; Computer Science ; Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Computer Science, Theory & Methods ; Computer Vision ; Convolutional neural network ; Cryptography ; Deep learning ; Design ; Digital imaging ; Experiments ; Feature extraction ; Image classification ; Image enhancement ; Machine learning ; Neural networks ; Science & Technology ; Security and Privacy ; Stability ; Steganalysis ; Steganography ; Strategy ; Technology ; Training ; Wavelet transforms</subject><ispartof>PeerJ. Computer science, 2021-04, Vol.7, p.e451-e451, Article 451</ispartof><rights>2021 Tabares-Soto et al.</rights><rights>COPYRIGHT 2021 PeerJ. Ltd.</rights><rights>2021 Tabares-Soto et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: https://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 Tabares-Soto et al. 2021 Tabares-Soto et al.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>13</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000639292900001</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c579t-f1ee4847ea637dea0803b7d47b87d45601cba13b374bd3d38f0f4c79923d6a903</citedby><cites>FETCH-LOGICAL-c579t-f1ee4847ea637dea0803b7d47b87d45601cba13b374bd3d38f0f4c79923d6a903</cites><orcidid>0000-0002-2341-5079 ; 0000-0001-5991-8770</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8049123/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8049123/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,729,782,786,866,887,2106,2118,27933,27934,39267,53800,53802</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33954236$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tabares-Soto, Reinel</creatorcontrib><creatorcontrib>Brayan Arteaga-Arteaga, Harold</creatorcontrib><creatorcontrib>Mora-Rubio, Alejandro</creatorcontrib><creatorcontrib>Alejandro Bravo-Ortiz, Mario</creatorcontrib><creatorcontrib>Arias-Garzon, Daniel</creatorcontrib><creatorcontrib>Alzate Grisales, Jesus Alejandro</creatorcontrib><creatorcontrib>Burbano Jacome, Alejandro</creatorcontrib><creatorcontrib>Orozco-Arias, Simon</creatorcontrib><creatorcontrib>Isaza, Gustavo</creatorcontrib><creatorcontrib>Ramos Pollan, Raul</creatorcontrib><title>Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain</title><title>PeerJ. Computer science</title><addtitle>PEERJ COMPUT SCI</addtitle><addtitle>PeerJ Comput Sci</addtitle><description>In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving steganographic images' detection accuracy, but it is unclear which computational elements are relevant. Here we present a strategy to improve accuracy, convergence, and stability during training. The strategy involves a preprocessing stage with Spatial Rich Models filters, Spatial Dropout, Absolute Value layer, and Batch Normalization. Using the strategy improves the performance of three steganalysis CNNs and two image classification CNNs by enhancing the accuracy from 2% up to 10% while reducing the training time to less than 6 h and improving the networks' stability.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Analysis</subject><subject>Artificial Intelligence</subject><subject>Artificial neural networks</subject><subject>Cable television broadcasting industry</subject><subject>Classification</subject><subject>Computer architecture</subject><subject>Computer Science</subject><subject>Computer Science, Artificial Intelligence</subject><subject>Computer Science, Information Systems</subject><subject>Computer Science, Theory & Methods</subject><subject>Computer Vision</subject><subject>Convolutional neural network</subject><subject>Cryptography</subject><subject>Deep learning</subject><subject>Design</subject><subject>Digital imaging</subject><subject>Experiments</subject><subject>Feature extraction</subject><subject>Image classification</subject><subject>Image enhancement</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Science & Technology</subject><subject>Security and Privacy</subject><subject>Stability</subject><subject>Steganalysis</subject><subject>Steganography</subject><subject>Strategy</subject><subject>Technology</subject><subject>Training</subject><subject>Wavelet transforms</subject><issn>2376-5992</issn><issn>2376-5992</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>HGBXW</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>DOA</sourceid><recordid>eNqNks2O0zAUhSMEYkZldqxRJDYgaLHjxE42SKOKn0ojITGwthz7JuOSxsF2OvQVeGpu2qFMEQtiKbbs756bHJ8keUrJQggq3gwAfj3XYZEX9EFynjHB50VVZQ_vrc-SixDWhBBaUHyqx8kZY1WRZ4yfJz-vo1cR2l0aXWo3g3dbSOMNpErr0Su9S12TatdvXTdG63rVpT3gwTTFW-e_pcrrGxtBx9FDSNUwdBbMpGZsayOCdqNaSAM2UVi-Czaktt_3CIOKFgnjNsr2T5JHjeoCXNzNs-Tr-3dflh_nV58-rJaXV3NdiCrOGwqQl7kAxZkwoEhJWC1MLuoS3wUnVNeKspqJvDbMsLIhTa4FGsEMVxVhs2R10DVOreXg8fv8Tjpl5X7D-VYqH63uQIIuaqNyyDlROcqXWc3rAnJFTIMeUtR6e9AaxnoDRkOPdnYnoqcnvb2RrdvKkuQVzRgKvLgT8O77CCHKjQ0auk714MYgsyLLOC1EKRB9_he6dqNHSyeKoh7hBftDtQp_wPaNw756EpWXfNKpON78LFn8g8JhYGPxuqGxuH9S8PKkAJkIP2KrxhDk6vrzKfv6wGrvQvDQHP2gRE6xlfvYSh0kxhbxZ_c9PMK_Q4pAeQBuoXZN0BZ6DUcMg81ZleEgU8aXmLkpqEs39hFLX_1_KfsFkJwMJQ</recordid><startdate>20210409</startdate><enddate>20210409</enddate><creator>Tabares-Soto, Reinel</creator><creator>Brayan Arteaga-Arteaga, Harold</creator><creator>Mora-Rubio, Alejandro</creator><creator>Alejandro Bravo-Ortiz, Mario</creator><creator>Arias-Garzon, Daniel</creator><creator>Alzate Grisales, Jesus Alejandro</creator><creator>Burbano Jacome, Alejandro</creator><creator>Orozco-Arias, Simon</creator><creator>Isaza, Gustavo</creator><creator>Ramos Pollan, Raul</creator><general>Peerj Inc</general><general>PeerJ. Ltd</general><general>PeerJ, Inc</general><general>PeerJ Inc</general><scope>BLEPL</scope><scope>DTL</scope><scope>HGBXW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>3V.</scope><scope>7XB</scope><scope>8AL</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>M0N</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-2341-5079</orcidid><orcidid>https://orcid.org/0000-0001-5991-8770</orcidid></search><sort><creationdate>20210409</creationdate><title>Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain</title><author>Tabares-Soto, Reinel ; Brayan Arteaga-Arteaga, Harold ; Mora-Rubio, Alejandro ; Alejandro Bravo-Ortiz, Mario ; Arias-Garzon, Daniel ; Alzate Grisales, Jesus Alejandro ; Burbano Jacome, Alejandro ; Orozco-Arias, Simon ; Isaza, Gustavo ; Ramos Pollan, Raul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c579t-f1ee4847ea637dea0803b7d47b87d45601cba13b374bd3d38f0f4c79923d6a903</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Analysis</topic><topic>Artificial Intelligence</topic><topic>Artificial neural networks</topic><topic>Cable television broadcasting industry</topic><topic>Classification</topic><topic>Computer architecture</topic><topic>Computer Science</topic><topic>Computer Science, Artificial Intelligence</topic><topic>Computer Science, Information Systems</topic><topic>Computer Science, Theory & Methods</topic><topic>Computer Vision</topic><topic>Convolutional neural network</topic><topic>Cryptography</topic><topic>Deep learning</topic><topic>Design</topic><topic>Digital imaging</topic><topic>Experiments</topic><topic>Feature extraction</topic><topic>Image classification</topic><topic>Image enhancement</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Science & Technology</topic><topic>Security and Privacy</topic><topic>Stability</topic><topic>Steganalysis</topic><topic>Steganography</topic><topic>Strategy</topic><topic>Technology</topic><topic>Training</topic><topic>Wavelet transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tabares-Soto, Reinel</creatorcontrib><creatorcontrib>Brayan Arteaga-Arteaga, Harold</creatorcontrib><creatorcontrib>Mora-Rubio, Alejandro</creatorcontrib><creatorcontrib>Alejandro Bravo-Ortiz, Mario</creatorcontrib><creatorcontrib>Arias-Garzon, Daniel</creatorcontrib><creatorcontrib>Alzate Grisales, Jesus Alejandro</creatorcontrib><creatorcontrib>Burbano Jacome, Alejandro</creatorcontrib><creatorcontrib>Orozco-Arias, Simon</creatorcontrib><creatorcontrib>Isaza, Gustavo</creatorcontrib><creatorcontrib>Ramos Pollan, Raul</creatorcontrib><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>Web of Science - Science Citation Index Expanded - 2021</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Computing Database (Alumni Edition)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Computing Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>PeerJ. Computer science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tabares-Soto, Reinel</au><au>Brayan Arteaga-Arteaga, Harold</au><au>Mora-Rubio, Alejandro</au><au>Alejandro Bravo-Ortiz, Mario</au><au>Arias-Garzon, Daniel</au><au>Alzate Grisales, Jesus Alejandro</au><au>Burbano Jacome, Alejandro</au><au>Orozco-Arias, Simon</au><au>Isaza, Gustavo</au><au>Ramos Pollan, Raul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain</atitle><jtitle>PeerJ. Computer science</jtitle><stitle>PEERJ COMPUT SCI</stitle><addtitle>PeerJ Comput Sci</addtitle><date>2021-04-09</date><risdate>2021</risdate><volume>7</volume><spage>e451</spage><epage>e451</epage><pages>e451-e451</pages><artnum>451</artnum><artnum>e451</artnum><issn>2376-5992</issn><eissn>2376-5992</eissn><abstract>In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving steganographic images' detection accuracy, but it is unclear which computational elements are relevant. Here we present a strategy to improve accuracy, convergence, and stability during training. The strategy involves a preprocessing stage with Spatial Rich Models filters, Spatial Dropout, Absolute Value layer, and Batch Normalization. Using the strategy improves the performance of three steganalysis CNNs and two image classification CNNs by enhancing the accuracy from 2% up to 10% while reducing the training time to less than 6 h and improving the networks' stability.</abstract><cop>LONDON</cop><pub>Peerj Inc</pub><pmid>33954236</pmid><doi>10.7717/peerj-cs.451</doi><tpages>21</tpages><orcidid>https://orcid.org/0000-0002-2341-5079</orcidid><orcidid>https://orcid.org/0000-0001-5991-8770</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2376-5992 |
| ispartof | PeerJ. Computer science, 2021-04, Vol.7, p.e451-e451, Article 451 |
| issn | 2376-5992 2376-5992 |
| language | eng |
| recordid | cdi_gale_infotracmisc_A657879642 |
| source | DOAJ Directory of Open Access Journals; Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" />; EZB-FREE-00999 freely available EZB journals; PubMed Central |
| subjects | Accuracy Algorithms Analysis Artificial Intelligence Artificial neural networks Cable television broadcasting industry Classification Computer architecture Computer Science Computer Science, Artificial Intelligence Computer Science, Information Systems Computer Science, Theory & Methods Computer Vision Convolutional neural network Cryptography Deep learning Design Digital imaging Experiments Feature extraction Image classification Image enhancement Machine learning Neural networks Science & Technology Security and Privacy Stability Steganalysis Steganography Strategy Technology Training Wavelet transforms |
| title | Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-03T09%3A36%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_webof&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Strategy%20to%20improve%20the%20accuracy%20of%20convolutional%20neural%20network%20architectures%20applied%20to%20digital%20image%20steganalysis%20in%20the%20spatial%20domain&rft.jtitle=PeerJ.%20Computer%20science&rft.au=Tabares-Soto,%20Reinel&rft.date=2021-04-09&rft.volume=7&rft.spage=e451&rft.epage=e451&rft.pages=e451-e451&rft.artnum=451&rft.issn=2376-5992&rft.eissn=2376-5992&rft_id=info:doi/10.7717/peerj-cs.451&rft_dat=%3Cgale_webof%3EA657879642%3C/gale_webof%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2510490653&rft_id=info:pmid/33954236&rft_galeid=A657879642&rft_doaj_id=oai_doaj_org_article_ec5bda4e460a487d82b6b5e4a0df3391&rfr_iscdi=true |