{"id":"https://openalex.org/W7117973579","doi":"https://doi.org/10.1145/3748522.3779992","title":"SourceBroken: A large-scale analysis on the (un)reliability of SourceRank in the PyPI ecosystem","display_name":"SourceBroken: A large-scale analysis on the (un)reliability of SourceRank in the PyPI ecosystem","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7117973579","doi":"https://doi.org/10.1145/3748522.3779992"},"language":null,"primary_location":{"id":"doi:10.1145/3748522.3779992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779992","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 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748522.3779992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121782962","display_name":"Biagio Montaruli","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Biagio Montaruli","raw_affiliation_strings":["EURECOM, Biot, France","SAP, Mougins, France"],"raw_orcid":"https://orcid.org/0009-0002-6870-8075","affiliations":[{"raw_affiliation_string":"EURECOM, Biot, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"SAP, Mougins, France","institution_ids":["https://openalex.org/I4210133526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035492762","display_name":"Serena Elisa Ponta","orcid":"https://orcid.org/0000-0002-6208-4743"},"institutions":[{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Serena Elisa Ponta","raw_affiliation_strings":["SAP, Mougins, France"],"raw_orcid":"https://orcid.org/0000-0002-6208-4743","affiliations":[{"raw_affiliation_string":"SAP, Mougins, France","institution_ids":["https://openalex.org/I4210133526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071893704","display_name":"Luca Compagna","orcid":"https://orcid.org/0009-0003-1072-4352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Compagna","raw_affiliation_strings":["Endor Labs, Palo Alto, USA"],"raw_orcid":"https://orcid.org/0009-0003-1072-4352","affiliations":[{"raw_affiliation_string":"Endor Labs, Palo Alto, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002025561","display_name":"Davide Balzarotti","orcid":"https://orcid.org/0000-0001-5957-6213"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Davide Balzarotti","raw_affiliation_strings":["EURECOM, Biot, France"],"raw_orcid":"https://orcid.org/0000-0001-5957-6213","affiliations":[{"raw_affiliation_string":"EURECOM, Biot, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1664","last_page":"1672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.8535000085830688,"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":0.8535000085830688,"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":0.07500000298023224,"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/T10734","display_name":"Information and Cyber Security","score":0.017799999564886093,"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/evasion","display_name":"Evasion (ethics)","score":0.8697999715805054},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.767300009727478},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7522000074386597},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6254000067710876},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/ecosystem","display_name":"Ecosystem","score":0.3806000053882599}],"concepts":[{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.8697999715805054},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.767300009727478},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7522000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253000140190125},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C110872660","wikidata":"https://www.wikidata.org/wiki/Q37813","display_name":"Ecosystem","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.27720001339912415}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3748522.3779992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779992","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 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.24400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.24400","pdf_url":"https://arxiv.org/pdf/2512.24400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3748522.3779992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779992","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 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6085169911384583},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4158247709274292}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"SourceRank":[0,100,108,164,230],"is":[1,218],"a":[2,54,81,85,124,138,162],"scoring":[3],"system":[4],"made":[5],"of":[6,15,39,75,99,110,127,232],"18":[7,77],"metrics":[8,78,231],"that":[9,57,193],"assess":[10],"the":[11,37,66,76,91,97,102,107,116,146,229],"popularity":[12],"and":[13,112,143,173,225],"quality":[14],"open-source":[16],"packages.":[17,129,234],"Despite":[18],"being":[19],"used":[20,168,220],"in":[21,101,115,123,176,207,211],"several":[22],"recent":[23],"studies,":[24],"none":[25],"has":[26],"thoroughly":[27],"analyzed":[28],"its":[29,202],"reliability":[30,98],"against":[31],"evasion":[32,60,223],"attacks":[33],"aimed":[34],"at":[35],"inflating":[36],"score":[38],"malicious":[40,92,113,144,174,233],"packages,":[41,145],"thereby":[42],"masquerading":[43],"them":[44],"as":[45,120,122],"trustworthy.":[46],"To":[47],"fill":[48],"this":[49,216],"gap,":[50],"we":[51,95],"first":[52],"propose":[53],"threat":[55],"model":[56],"identifies":[58],"potential":[59],"approaches":[61],"for":[62],"each":[63],"metric,":[64],"including":[65],"URL":[67,82,194],"confusion":[68,195],"technique,":[69],"which":[70],"can":[71,226],"affect":[72],"5":[73],"out":[74],"by":[79,105],"leveraging":[80],"pointing":[83],"to":[84,90,153,156,169,180,209],"legitimate":[86],"repository":[87],"potentially":[88],"unrelated":[89],"package.":[93],"Furthermore,":[94],"study":[96],"PyPI":[103],"ecosystem":[104],"analyzing":[106],"distributions":[109,148],"benign":[111,142,172,182],"packages":[114,175,183],"state-of-the-art":[117],"MalwareBench":[118,208],"dataset,":[119],"well":[121],"real-world":[125,147,177,213],"dataset":[126],"122,398":[128],"Our":[130],"analysis":[131,191],"reveals":[132,192],"that,":[133],"while":[134],"historical":[135],"data":[136],"suggests":[137],"clear":[139],"distinction":[140],"between":[141,171],"overlap":[149],"significantly,":[150],"mainly":[151],"due":[152],"SourceRank's":[154],"failure":[155],"timely":[157],"reflect":[158],"package":[159],"removals.":[160],"As":[161],"result,":[163],"cannot":[165],"be":[166],"reliably":[167],"discriminate":[170],"scenarios,":[178],"nor":[179],"select":[181],"among":[184],"those":[185],"available":[186],"on":[187],"PyPI.":[188],"Finally,":[189],"our":[190,212],"represents":[196],"an":[197],"emerging":[198],"attack":[199],"vector,":[200],"with":[201],"prevalence":[203],"increasing":[204],"from":[205],"4.2%":[206],"7.0%":[210],"dataset.":[214],"Moreover,":[215],"technique":[217],"often":[219],"alongside":[221],"other":[222],"techniques":[224],"significantly":[227],"inflate":[228]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-02T00:00:00"}