OcrV1, Main, Exploration, bibRecord, 000120

The Robustness of "Connecting Characters Together" CAPTCHAs

Identifieur interne : 000120 ( Main/Exploration ); précédent : 000119; suivant : 000121

The Robustness of "Connecting Characters Together" CAPTCHAs

Auteurs : HAICHANG GAO [République populaire de Chine] ; WEI WANG [République populaire de Chine] ; YE FAN [République populaire de Chine] ; JIAO QI [République populaire de Chine] ; XIYANG LIU [République populaire de Chine]

Source :

Journal of information science and engineering [ 1016-2364 ] ; 2014.

RBID : Pascal:14-0081341

Descripteurs français

Pascal (Inist)
- Authentification, Interface utilisateur, Sécurité informatique, Texte, Navigation information, Analyse documentaire, Reconnaissance caractère, Reconnaissance forme, Traitement image, Reconnaissance optique caractère, Robustesse, Segmentation, ..

English descriptors

KwdEn :
- Authentication, Character recognition, Computer security, Document analysis, Image processing, Information browsing, Optical character recognition, Pattern recognition, Robustness, Segmentation, Text, User interface.

Abstract

CAPTCHA is now commonly used as standard security technology to tell computers and humans apart. The most widely deployed CAPTCHAs are text-based schemes. In this paper, we document how we have broken such a text-based scheme which uses the "connecting characters together (CCT)" principle. CAPTCHAs of this type can be classified into three types: CAPTCHA with overlap but no noise arcs; CAPTCHA with noise arcs but no overlap; and CAPTCHA without noise arcs and overlap. Yahoo!, Baidu CAPTCHA and reCAPTCHA were selected as representatives of the three types. The CCT CAPTCHA is effectively resistant to segmentation and recognition in the early attacks. In contrast to early works that recognized the text after segmentation, we combined recognition with segmentation to break the CCT CAPTCHA. Our method segments the text by extracting the recognized characters. The experiments show that our extraction and segmentation attack on Yahoo! CAPTCHA achieved a success rate of 78% and an overall (individual character recognition with OCR) success rate of 55%. The segmentation and recognition success rate of Baidu CAPTCHA was 34%. On re- CAPTCHA we achieved 34% success rate.

Affiliations:

République populaire de Chine

Links toward previous steps (curation, corpus...)

to stream PascalFrancis, to step Corpus: 000024
to stream PascalFrancis, to step Curation: 000740
to stream PascalFrancis, to step Checkpoint: 000003
to stream Main, to step Merge: 000121
to stream Main, to step Curation: 000120

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">The Robustness of "Connecting Characters Together" CAPTCHAs</title>
<author><name sortKey="Haichang Gao" sort="Haichang Gao" uniqKey="Haichang Gao" last="Haichang Gao">HAICHANG GAO</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Wei Wang" sort="Wei Wang" uniqKey="Wei Wang" last="Wei Wang">WEI WANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Ye Fan" sort="Ye Fan" uniqKey="Ye Fan" last="Ye Fan">YE FAN</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Jiao Qi" sort="Jiao Qi" uniqKey="Jiao Qi" last="Jiao Qi">JIAO QI</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Xiyang Liu" sort="Xiyang Liu" uniqKey="Xiyang Liu" last="Xiyang Liu">XIYANG LIU</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">14-0081341</idno>
<date when="2014">2014</date>
<idno type="stanalyst">PASCAL 14-0081341 INIST</idno>
<idno type="RBID">Pascal:14-0081341</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000024</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000740</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000003</idno>
<idno type="wicri:doubleKey">1016-2364:2014:Haichang Gao:the:robustness:of</idno>
<idno type="wicri:Area/Main/Merge">000121</idno>
<idno type="wicri:Area/Main/Curation">000120</idno>
<idno type="wicri:Area/Main/Exploration">000120</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">The Robustness of "Connecting Characters Together" CAPTCHAs</title>
<author><name sortKey="Haichang Gao" sort="Haichang Gao" uniqKey="Haichang Gao" last="Haichang Gao">HAICHANG GAO</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Wei Wang" sort="Wei Wang" uniqKey="Wei Wang" last="Wei Wang">WEI WANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Ye Fan" sort="Ye Fan" uniqKey="Ye Fan" last="Ye Fan">YE FAN</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Jiao Qi" sort="Jiao Qi" uniqKey="Jiao Qi" last="Jiao Qi">JIAO QI</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Xiyang Liu" sort="Xiyang Liu" uniqKey="Xiyang Liu" last="Xiyang Liu">XIYANG LIU</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Software Engineering Institute, Xidian University</s1>
<s2>Xi'an, Shaanxi, 710071</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>Xi'an, Shaanxi, 710071</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Journal of information science and engineering</title>
<title level="j" type="abbreviated">J. inf. sci. eng.</title>
<idno type="ISSN">1016-2364</idno>
<imprint><date when="2014">2014</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Journal of information science and engineering</title>
<title level="j" type="abbreviated">J. inf. sci. eng.</title>
<idno type="ISSN">1016-2364</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Authentication</term>
<term>Character recognition</term>
<term>Computer security</term>
<term>Document analysis</term>
<term>Image processing</term>
<term>Information browsing</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Robustness</term>
<term>Segmentation</term>
<term>Text</term>
<term>User interface</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Authentification</term>
<term>Interface utilisateur</term>
<term>Sécurité informatique</term>
<term>Texte</term>
<term>Navigation information</term>
<term>Analyse documentaire</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance forme</term>
<term>Traitement image</term>
<term>Reconnaissance optique caractère</term>
<term>Robustesse</term>
<term>Segmentation</term>
<term>.</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">CAPTCHA is now commonly used as standard security technology to tell computers and humans apart. The most widely deployed CAPTCHAs are text-based schemes. In this paper, we document how we have broken such a text-based scheme which uses the "connecting characters together (CCT)" principle. CAPTCHAs of this type can be classified into three types: CAPTCHA with overlap but no noise arcs; CAPTCHA with noise arcs but no overlap; and CAPTCHA without noise arcs and overlap. Yahoo!, Baidu CAPTCHA and reCAPTCHA were selected as representatives of the three types. The CCT CAPTCHA is effectively resistant to segmentation and recognition in the early attacks. In contrast to early works that recognized the text after segmentation, we combined recognition with segmentation to break the CCT CAPTCHA. Our method segments the text by extracting the recognized characters. The experiments show that our extraction and segmentation attack on Yahoo! CAPTCHA achieved a success rate of 78% and an overall (individual character recognition with OCR) success rate of 55%. The segmentation and recognition success rate of Baidu CAPTCHA was 34%. On re- CAPTCHA we achieved 34% success rate.</div>
</front>
</TEI>
<affiliations><list><country><li>République populaire de Chine</li>
</country>
</list>
<tree><country name="République populaire de Chine"><noRegion><name sortKey="Haichang Gao" sort="Haichang Gao" uniqKey="Haichang Gao" last="Haichang Gao">HAICHANG GAO</name>
</noRegion>
<name sortKey="Jiao Qi" sort="Jiao Qi" uniqKey="Jiao Qi" last="Jiao Qi">JIAO QI</name>
<name sortKey="Wei Wang" sort="Wei Wang" uniqKey="Wei Wang" last="Wei Wang">WEI WANG</name>
<name sortKey="Xiyang Liu" sort="Xiyang Liu" uniqKey="Xiyang Liu" last="Xiyang Liu">XIYANG LIU</name>
<name sortKey="Ye Fan" sort="Ye Fan" uniqKey="Ye Fan" last="Ye Fan">YE FAN</name>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000120 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000120 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     Pascal:14-0081341
   |texte=   The Robustness of "Connecting Characters Together" CAPTCHAs
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

The Robustness of "Connecting Characters Together" CAPTCHAs

The Robustness of "Connecting Characters Together" CAPTCHAs

Source :

Descripteurs français

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri