{"id":"https://openalex.org/W3012731629","doi":"https://doi.org/10.1145/3366423.3380166","title":"A Generic Solver Combining Unsupervised Learning and Representation Learning for Breaking Text-Based Captchas","display_name":"A Generic Solver Combining Unsupervised Learning and Representation Learning for Breaking Text-Based Captchas","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3012731629","doi":"https://doi.org/10.1145/3366423.3380166","mag":"3012731629"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380166","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380166","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102970944","display_name":"Sheng Tian","orcid":"https://orcid.org/0000-0003-3756-5454"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sheng Tian","raw_affiliation_strings":["Ant Financial Services Group; Electronic Information School Wuhan University","Ant Financial Services Group"],"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group; Electronic Information School Wuhan University","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Ant Financial Services Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101439585","display_name":"Tao Xiong","orcid":"https://orcid.org/0000-0003-1583-8669"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Xiong","raw_affiliation_strings":["Ant Financial Services Group"],"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102970944"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":4.8043,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95462422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11800","display_name":"User Authentication and Security Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11800","display_name":"User Authentication and Security Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/captcha","display_name":"CAPTCHA","score":0.9764080047607422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8503026962280273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.636761486530304},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5840911865234375},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5653364658355713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5573691129684448},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5324597954750061},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4406864643096924},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4404624402523041},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.41291874647140503},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15064239501953125}],"concepts":[{"id":"https://openalex.org/C163339463","wikidata":"https://www.wikidata.org/wiki/Q484598","display_name":"CAPTCHA","level":2,"score":0.9764080047607422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503026962280273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.636761486530304},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5840911865234375},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5653364658355713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5573691129684448},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5324597954750061},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4406864643096924},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4404624402523041},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41291874647140503},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15064239501953125},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366423.3380166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380166","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380166","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380166","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1901129140","https://openalex.org/W1971657180","https://openalex.org/W1983320747","https://openalex.org/W2027237225","https://openalex.org/W2043165161","https://openalex.org/W2055013232","https://openalex.org/W2075785508","https://openalex.org/W2085351990","https://openalex.org/W2088301450","https://openalex.org/W2099256741","https://openalex.org/W2105523261","https://openalex.org/W2108501770","https://openalex.org/W2115601549","https://openalex.org/W2144409202","https://openalex.org/W2157331557","https://openalex.org/W2380581874","https://openalex.org/W2528437680","https://openalex.org/W2590796488","https://openalex.org/W2595089739","https://openalex.org/W2619371851","https://openalex.org/W2734358244","https://openalex.org/W2766473095","https://openalex.org/W2794632300","https://openalex.org/W2842511635","https://openalex.org/W2890419535","https://openalex.org/W2896013314","https://openalex.org/W2911353848","https://openalex.org/W2911779594","https://openalex.org/W2914997028","https://openalex.org/W2920515971","https://openalex.org/W2944828972","https://openalex.org/W4293428270","https://openalex.org/W6738597727"],"related_works":["https://openalex.org/W3134776999","https://openalex.org/W1975364925","https://openalex.org/W2064097623","https://openalex.org/W2566963304","https://openalex.org/W2770704788","https://openalex.org/W2028308373","https://openalex.org/W2111502540","https://openalex.org/W1502766620","https://openalex.org/W3048601286","https://openalex.org/W2965925734"],"abstract_inverted_index":{"Although":[0],"there":[1],"are":[2,10],"many":[3],"alternative":[4],"captcha":[5,50,169],"schemes":[6],"available,":[7],"text-based":[8,99,197],"captchas":[9,44,96],"still":[11],"one":[12],"of":[13,34,42,73,95,115,123,143,175,178,196],"the":[14,29,37,71,92,121,140,148,157,179,190,194],"most":[15],"popular":[16],"security":[17,22,75,195],"mechanism":[18],"to":[19,28,89,119,192],"maintain":[20],"Internet":[21],"and":[23,32,53,66,86,97,138],"prevent":[24],"malicious":[25],"attacks,":[26],"due":[27],"user":[30],"preferences":[31],"ease":[33],"design.":[35],"Over":[36],"past":[38],"decade,":[39],"different":[40],"methods":[41],"breaking":[43],"have":[45],"been":[46],"proposed,":[47],"which":[48,110],"helps":[49],"keep":[51],"evolving":[52],"become":[54,68],"more":[55],"robust.":[56],"However,":[57],"these":[58],"previous":[59],"works":[60],"generally":[61],"require":[62],"heavy":[63],"expert":[64],"involvement":[65],"gradually":[67],"ineffective":[69],"with":[70,147],"introduction":[72],"new":[74,104],"features.":[76],"This":[77],"paper":[78],"proposes":[79],"a":[80,103,112,144,164],"generic":[81],"solver":[82],"combining":[83],"unsupervised":[84],"learning":[85,88,129],"representation":[87,124],"automatically":[90],"remove":[91],"noisy":[93],"background":[94],"solve":[98],"captchas.":[100,198],"We":[101,171,183],"introduce":[102],"training":[105],"scheme":[106],"for":[107],"constructing":[108],"mini-batches,":[109],"contain":[111],"large":[113],"number":[114],"unlabeled":[116],"hard":[117],"examples,":[118],"improve":[120],"efficiency":[122],"learning.":[125],"Unlike":[126],"existing":[127],"deep":[128],"algorithms,":[130],"our":[131,186],"method":[132,159],"requires":[133],"significantly":[134],"fewer":[135],"labeled":[136],"samples":[137],"surpasses":[139],"recognition":[141],"performance":[142],"fully-supervised":[145],"model":[146],"same":[149],"network":[150],"architecture.":[151],"Moreover,":[152],"extensive":[153],"experiments":[154],"show":[155],"that":[156,185],"proposed":[158,180],"outperforms":[160],"state-of-the-art":[161],"by":[162],"delivering":[163],"higher":[165],"accuracy":[166],"on":[167],"various":[168],"schemes.":[170],"provide":[172],"further":[173],"discussions":[174],"potential":[176],"applications":[177],"unified":[181],"framework.":[182],"hope":[184],"work":[187],"can":[188],"inspire":[189],"community":[191],"enhance":[193]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}