{"id":"https://openalex.org/W4287851280","doi":"https://doi.org/10.1109/spw54247.2022.9833862","title":"Statistical detection of format dialects using the weighted Dowker complex","display_name":"Statistical detection of format dialects using the weighted Dowker complex","publication_year":2022,"publication_date":"2022-05-01","ids":{"openalex":"https://openalex.org/W4287851280","doi":"https://doi.org/10.1109/spw54247.2022.9833862"},"language":"en","primary_location":{"id":"doi:10.1109/spw54247.2022.9833862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spw54247.2022.9833862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Security and Privacy Workshops (SPW)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032354259","display_name":"Michael Robinson","orcid":"https://orcid.org/0000-0003-0766-3301"},"institutions":[{"id":"https://openalex.org/I181401687","display_name":"American University","ror":"https://ror.org/052w4zt36","country_code":"US","type":"education","lineage":["https://openalex.org/I181401687"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Robinson","raw_affiliation_strings":["American University,Department of Mathematics and Statistics,Washington,DC","Department of Mathematics and Statistics, American University, Washington, DC"],"affiliations":[{"raw_affiliation_string":"American University,Department of Mathematics and Statistics,Washington,DC","institution_ids":["https://openalex.org/I181401687"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, American University, Washington, DC","institution_ids":["https://openalex.org/I181401687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109386445","display_name":"Cory Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117222","display_name":"BAE Systems (United States)","ror":"https://ror.org/02fctgp09","country_code":"US","type":"company","lineage":["https://openalex.org/I4210117222","https://openalex.org/I4210143731"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cory Anderson","raw_affiliation_strings":["BAE Systems FAST Labs,Arlington,VA","BAE Systems FAST Labs, Arlington, VA"],"affiliations":[{"raw_affiliation_string":"BAE Systems FAST Labs,Arlington,VA","institution_ids":["https://openalex.org/I4210117222"]},{"raw_affiliation_string":"BAE Systems FAST Labs, Arlington, VA","institution_ids":["https://openalex.org/I4210117222"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020379889","display_name":"Letitia W. Li","orcid":"https://orcid.org/0000-0002-8373-6042"},"institutions":[{"id":"https://openalex.org/I4210117222","display_name":"BAE Systems (United States)","ror":"https://ror.org/02fctgp09","country_code":"US","type":"company","lineage":["https://openalex.org/I4210117222","https://openalex.org/I4210143731"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Letitia W. Li","raw_affiliation_strings":["BAE Systems FAST Labs,Arlington,VA","BAE Systems FAST Labs, Arlington, VA"],"affiliations":[{"raw_affiliation_string":"BAE Systems FAST Labs,Arlington,VA","institution_ids":["https://openalex.org/I4210117222"]},{"raw_affiliation_string":"BAE Systems FAST Labs, Arlington, VA","institution_ids":["https://openalex.org/I4210117222"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077962548","display_name":"Steve Huntsman","orcid":"https://orcid.org/0000-0002-9168-2216"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steve Huntsman","raw_affiliation_strings":["Arlington,VA","Arlington, VA"],"affiliations":[{"raw_affiliation_string":"Arlington,VA","institution_ids":[]},{"raw_affiliation_string":"Arlington, VA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032354259"],"corresponding_institution_ids":["https://openalex.org/I181401687"],"apc_list":null,"apc_paid":null,"fwci":0.6897,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74849772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.989799976348877,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.742153525352478},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6820871233940125},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6548884510993958},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5341692566871643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4709504544734955},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.45785319805145264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44787344336509705},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4148463010787964},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33515405654907227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1492302417755127},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14415308833122253},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14007538557052612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742153525352478},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6820871233940125},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6548884510993958},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5341692566871643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4709504544734955},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.45785319805145264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44787344336509705},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4148463010787964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33515405654907227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1492302417755127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14415308833122253},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14007538557052612},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spw54247.2022.9833862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spw54247.2022.9833862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Security and Privacy Workshops (SPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W60603402","https://openalex.org/W1777157359","https://openalex.org/W2102637390","https://openalex.org/W2183877827","https://openalex.org/W2280242822","https://openalex.org/W2779064420","https://openalex.org/W2784113120","https://openalex.org/W2902696364","https://openalex.org/W2940752008","https://openalex.org/W3007346474","https://openalex.org/W3008443479","https://openalex.org/W3031879401","https://openalex.org/W3087355157","https://openalex.org/W3099161928","https://openalex.org/W3123969097","https://openalex.org/W3182567581","https://openalex.org/W6602539855","https://openalex.org/W6638033346","https://openalex.org/W6774620520","https://openalex.org/W6779263206"],"related_works":["https://openalex.org/W2953058328","https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2750730210","https://openalex.org/W2116854923","https://openalex.org/W2236974868","https://openalex.org/W4312766348","https://openalex.org/W4381248170","https://openalex.org/W2817971408","https://openalex.org/W3189621521"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"an":[3],"experimentally":[4],"validated,":[5],"probabilistic":[6],"model":[7,58],"of":[8,16,25,29,50,85,95,119,125],"file":[9,45,96],"behavior":[10,20],"when":[11],"consumed":[12],"by":[13,23],"a":[14,26,44,47,54,60,80,132],"set":[15,28,49,82],"pre-existing":[17],"parsers.":[18],"File":[19],"is":[21,52],"measured":[22],"way":[24],"standardized":[27],"Boolean":[30],"\"messages\"":[31],"produced":[32],"as":[33],"the":[34,40,89,92,145],"files":[35,146],"are":[36,128],"read.":[37],"By":[38,140],"thresholding":[39,71],"posterior":[41],"probability":[42],"that":[43,69,147],"exhibiting":[46],"particular":[48,55],"messages":[51,120],"from":[53,79],"dialect,":[56],"our":[57],"yields":[59],"practical":[61],"classification":[62,103,107],"algorithm":[63,72],"for":[64,73,98,160],"two":[65,74],"dialects.":[66,139],"We":[67],"demonstrate":[68],"this":[70,126],"dialects":[75],"can":[76,154],"be":[77],"bootstrapped":[78],"training":[81],"consisting":[83],"primarily":[84],"one":[86,99],"dialect.":[87,123],"Both":[88],"theoretical":[90,113],"and":[91,105,130],"empirical":[93],"distributions":[94],"behaviors":[97],"dialect":[100,161],"yield":[101],"good":[102],"performance,":[104],"outperform":[106],"based":[108],"on":[109,116],"simply":[110],"counting":[111],"messages.Our":[112],"framework":[114],"relies":[115],"statistical":[117],"independence":[118],"within":[121,149],"each":[122],"Violations":[124],"assumption":[127],"detectable":[129],"allow":[131],"format":[133,152],"analyst":[134],"to":[135,144],"identify":[136],"\"boundaries\"":[137],"between":[138],"restricting":[141],"their":[142],"attention":[143],"lie":[148],"these":[150],"boundaries,":[151],"analysts":[153],"more":[155],"efficiently":[156],"craft":[157],"new":[158],"criteria":[159],"detection.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}