{"id":"https://openalex.org/W4318210353","doi":"https://doi.org/10.1145/3543507.3583326","title":"An Empirical Study of the Usage of Checksums for Web Downloads","display_name":"An Empirical Study of the Usage of Checksums for Web Downloads","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4318210353","doi":"https://doi.org/10.1145/3543507.3583326"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583326","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 ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3543507.3583326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056628341","display_name":"Ga\u00ebl Bernard","orcid":"https://orcid.org/0000-0001-7299-1286"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Ga\u00ebl Bernard","raw_affiliation_strings":["EPFL, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-7299-1286","affiliations":[{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060835450","display_name":"R\u00e9mi Coudert","orcid":"https://orcid.org/0000-0002-4784-568X"},"institutions":[{"id":"https://openalex.org/I97565354","display_name":"University of Lausanne","ror":"https://ror.org/019whta54","country_code":"CH","type":"education","lineage":["https://openalex.org/I97565354"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"R\u00e9mi Coudert","raw_affiliation_strings":["Department of Information Systems, University of Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4784-568X","affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Lausanne, Switzerland","institution_ids":["https://openalex.org/I97565354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031241829","display_name":"Bertil Chapuis","orcid":"https://orcid.org/0000-0003-3168-5375"},"institutions":[{"id":"https://openalex.org/I173439891","display_name":"HES-SO University of Applied Sciences and Arts Western Switzerland","ror":"https://ror.org/01xkakk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bertil Chapuis","raw_affiliation_strings":["University of Applied Sciences Western Switzerland, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3168-5375","affiliations":[{"raw_affiliation_string":"University of Applied Sciences Western Switzerland, Switzerland","institution_ids":["https://openalex.org/I173439891"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017780534","display_name":"K\u00e9vin Huguenin","orcid":"https://orcid.org/0000-0001-7147-1828"},"institutions":[{"id":"https://openalex.org/I97565354","display_name":"University of Lausanne","ror":"https://ror.org/019whta54","country_code":"CH","type":"education","lineage":["https://openalex.org/I97565354"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"K\u00e9vin Huguenin","raw_affiliation_strings":["Department of Information Systems, University of Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-7147-1828","affiliations":[{"raw_affiliation_string":"Department of Information Systems, University of Lausanne, Switzerland","institution_ids":["https://openalex.org/I97565354"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056628341"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00557103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2155","last_page":"2165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998000264167786,"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":0.9986000061035156,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9950000047683716,"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/checksum","display_name":"Checksum","score":0.9716120958328247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132437467575073},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7441413402557373},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7423171997070312},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5156227946281433},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.4495667815208435},{"id":"https://openalex.org/keywords/cryptographic-hash-function","display_name":"Cryptographic hash function","score":0.4325179159641266},{"id":"https://openalex.org/keywords/hash-tree","display_name":"Hash tree","score":0.4155050814151764},{"id":"https://openalex.org/keywords/md5","display_name":"MD5","score":0.41115128993988037},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40913110971450806},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32143712043762207},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19004860520362854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1663091778755188},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.15146610140800476}],"concepts":[{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.9716120958328247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132437467575073},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7441413402557373},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7423171997070312},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5156227946281433},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.4495667815208435},{"id":"https://openalex.org/C7608002","wikidata":"https://www.wikidata.org/wiki/Q477202","display_name":"Cryptographic hash function","level":3,"score":0.4325179159641266},{"id":"https://openalex.org/C27353603","wikidata":"https://www.wikidata.org/wiki/Q16948622","display_name":"Hash tree","level":4,"score":0.4155050814151764},{"id":"https://openalex.org/C157172786","wikidata":"https://www.wikidata.org/wiki/Q185235","display_name":"MD5","level":3,"score":0.41115128993988037},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40913110971450806},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32143712043762207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19004860520362854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1663091778755188},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.15146610140800476}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3543507.3583326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583326","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 ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03956972v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03956972","pdf_url":"https://hal.science/hal-03956972v1/file/Bernard2023WWW.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www2023.thewebconf.org","raw_type":"Conference papers"},{"id":"pmh:oai:iris.unil.ch:iris/155210","is_oa":true,"landing_page_url":"https://iris.unil.ch/handle/iris/155210","pdf_url":"https://iris.unil.ch/bitstreams/b7976c40-5f6a-4eb2-9d13-1b142af8a8df/download","source":{"id":"https://openalex.org/S7407055444","display_name":"IRIS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:serval.unil.ch:BIB_DB6F0918594E","is_oa":true,"landing_page_url":"https://serval.unil.ch/notice/serval:BIB_DB6F0918594E","pdf_url":"https://serval.unil.ch/resource/serval:BIB_DB6F0918594E.P001/REF.pdf","source":{"id":"https://openalex.org/S4306401797","display_name":"SERVAL (Universit\u00e9 de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210093590","host_organization_name":"Swiss School of Archaeology in Greece","host_organization_lineage":["https://openalex.org/I4210093590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the WebConference (WWW), pp. 2155-\u200c2165","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:hesso.tind.io:15310","is_oa":false,"landing_page_url":"https://arodes.hes-so.ch/record/15310/files/Chapuis_2023_empirical_study_of_the_usage.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/15310","raw_type":"Text"},{"id":"pmh:oai:share.osf.io:E0072-FE1-46D","is_oa":false,"landing_page_url":"http://osf.io/a9ykr/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"project"}],"best_oa_location":{"id":"doi:10.1145/3543507.3583326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543507.3583326","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 ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3378801267","display_name":null,"funder_award_id":"19024","funder_id":"https://openalex.org/F4320321942","funder_display_name":"Hasler Stiftung"}],"funders":[{"id":"https://openalex.org/F4320321942","display_name":"Hasler Stiftung","ror":"https://ror.org/04m3t9183"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1656731780","https://openalex.org/W1975879668","https://openalex.org/W2103239853","https://openalex.org/W2155243985","https://openalex.org/W2164777277","https://openalex.org/W2477907264","https://openalex.org/W2605157885","https://openalex.org/W2610507852","https://openalex.org/W2757395016","https://openalex.org/W2890220547","https://openalex.org/W2903158431","https://openalex.org/W3002929229","https://openalex.org/W3089880085","https://openalex.org/W3117384287","https://openalex.org/W3128430109","https://openalex.org/W3137137791","https://openalex.org/W4238577395","https://openalex.org/W4281564584"],"related_works":["https://openalex.org/W2000606687","https://openalex.org/W3019380737","https://openalex.org/W4251738463","https://openalex.org/W3174323879","https://openalex.org/W2909045450","https://openalex.org/W2976219018","https://openalex.org/W3015987186","https://openalex.org/W2361992394","https://openalex.org/W2618944029","https://openalex.org/W2144354274"],"abstract_inverted_index":{"Checksums,":[0],"typically":[1],"provided":[2,163],"on":[3,22,41,164,195],"webpages":[4,118,126,165,188],"and":[5,65,72,155],"generated":[6],"from":[7,104],"cryptographic":[8],"hash":[9,150],"functions":[10,62,151],"(e.g.,":[11,17],"MD5,":[12],"SHA256)":[13],"or":[14],"signature":[15],"schemes":[16],"PGP),":[18],"are":[19,141,152],"commonly":[20],"used":[21,142],"websites":[23,71],"to":[24,27,144],"enable":[25],"users":[26],"verify":[28,145],"that":[29,119,139,148,156,169],"the":[30,50,54,88,94,131,161,183,186,196,199],"files":[31],"they":[32,202],"download":[33],"have":[34],"not":[35,167],"been":[36,78],"tampered":[37],"with":[38,179],"when":[39],"stored":[40],"possibly":[42],"untrusted":[43],"servers.":[44],"In":[45],"this":[46,76],"paper,":[47],"we":[48,96,106,175],"elucidate":[49],"current":[51],"practices":[52],"regarding":[53],"usage":[55,132],"of":[56,67,70,93,101,115,124,133,160,170,182,185],"checksums":[57,140,162],"for":[58,87],"web":[59],"downloads":[60],"(hash":[61],"used,":[63,154],"visibility":[64],"validity":[66],"checksums,":[68],"type":[69],"files,":[73,147],"etc.),":[74],"as":[75],"has":[77],"mostly":[79,143],"overlooked":[80],"so":[81],"far.":[82],"Using":[83],"a":[84,99,112,157,180],"snowball-sampling":[85],"strategy":[86],"200000":[89],"most":[90],"popular":[91],"domains":[92],"Web,":[95],"first":[97],"crawled":[98],"dataset":[100,114],"8.5M":[102],"webpages,":[103],"which":[105],"built,":[107],"through":[108],"an":[109],"active-learning":[110],"approach,":[111],"unique":[113],"277":[116],"diverse":[117],"contain":[120],"checksums.":[121,134],"Our":[122],"analysis":[123,178],"these":[125],"reveals":[127],"interesting":[128],"findings":[129],"about":[130],"For":[135],"instance,":[136],"it":[137],"shows":[138],"program":[146],"weak":[149],"frequently":[153],"non-negligible":[158],"proportion":[159],"do":[166],"match":[168],"their":[171],"associated":[172],"files.":[173],"Finally,":[174],"complement":[176],"our":[177],"survey":[181],"webmasters":[184],"considered":[187],"(N":[189],"=":[190],"26),":[191],"thus":[192],"shedding":[193],"light":[194],"reasons":[197],"behind":[198],"checksum-related":[200],"choices":[201],"make.":[203]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
