{"id":"https://openalex.org/W7117114436","doi":"https://doi.org/10.1145/3756681.3757042","title":"Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy","display_name":"Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W7117114436","doi":"https://doi.org/10.1145/3756681.3757042"},"language":null,"primary_location":{"id":"doi:10.1145/3756681.3757042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3757042","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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3756681.3757042","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120083968","display_name":"Motunrayo Osatohanmen Ibiyo","orcid":null},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Motunrayo Osatohanmen Ibiyo","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0009-0005-0308-8997","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121129026","display_name":"Thinakone Louangdy","orcid":null},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Thinakone Louangdy","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0009-0003-2883-3119","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111191577","display_name":"Phuong Thi Lan Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Phuong T. Nguyen","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3666-4162","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047553297","display_name":"Claudio Di Sipio","orcid":"https://orcid.org/0000-0001-9872-9542"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Di Sipio","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9872-9542","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002764716","display_name":"Davide Di Ruscio","orcid":"https://orcid.org/0000-0002-5077-6793"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Di Ruscio","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5077-6793","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics, University of L'Aquila, L'Aquila, L'Aquila, Italy","institution_ids":["https://openalex.org/I26415053"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83388066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.4927000105381012,"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":0.4927000105381012,"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/T10260","display_name":"Software Engineering Research","score":0.34700000286102295,"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/T11644","display_name":"Spam and Phishing Detection","score":0.03350000083446503,"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/counterintuitive","display_name":"Counterintuitive","score":0.728600025177002},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6179999709129333},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5755000114440918},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5091000199317932},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.40709999203681946},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3294999897480011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076000213623047},{"id":"https://openalex.org/C101097943","wikidata":"https://www.wikidata.org/wiki/Q5176983","display_name":"Counterintuitive","level":2,"score":0.728600025177002},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6179999709129333},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5755000114440918},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5209000110626221},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C77109596","wikidata":"https://www.wikidata.org/wiki/Q4781497","display_name":"Application security","level":5,"score":0.2671999931335449},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3756681.3757042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3757042","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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3756681.3757042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3757042","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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2133933998","https://openalex.org/W3036603968","https://openalex.org/W3080622597","https://openalex.org/W3107757457","https://openalex.org/W3160172209","https://openalex.org/W4241830954","https://openalex.org/W4312436517","https://openalex.org/W4367059011","https://openalex.org/W4388502419","https://openalex.org/W4392120462","https://openalex.org/W4392414327","https://openalex.org/W4399516345","https://openalex.org/W4399601909","https://openalex.org/W4401164081","https://openalex.org/W4401539489","https://openalex.org/W4402272476","https://openalex.org/W4402409840","https://openalex.org/W4402618494","https://openalex.org/W4403536721","https://openalex.org/W4404391292","https://openalex.org/W4406460462","https://openalex.org/W4407403777","https://openalex.org/W4410705984"],"related_works":[],"abstract_inverted_index":{"Malicious":[0],"software":[1],"packages":[2,17],"in":[3,104],"open-source":[4],"ecosystems,":[5],"such":[6],"as":[7,119],"PyPI,":[8],"pose":[9],"growing":[10],"security":[11],"risks.":[12],"Unlike":[13],"traditional":[14,136],"vulnerabilities,":[15],"these":[16],"are":[18],"intentionally":[19],"designed":[20],"to":[21,28,96],"deceive":[22],"users,":[23],"making":[24],"detection":[25,124],"challenging":[26],"due":[27],"evolving":[29],"attack":[30],"methods":[31],"and":[32,54,68,75,131,150],"the":[33,44,80,99,105,123],"lack":[34],"of":[35,46,82,125],"structured":[36,144],"datasets.":[37],"In":[38,112],"this":[39],"work,":[40],"we":[41],"empirically":[42],"evaluate":[43],"effectiveness":[45],"Large":[47],"Language":[48],"Models":[49],"(LLMs),":[50],"Retrieval-Augmented":[51],"Generation":[52],"(RAG),":[53],"few-shot":[55,114],"learning":[56,115],"for":[57],"detecting":[58],"malicious":[59,76,126],"source":[60],"code.":[61],"We":[62,86],"fine-tune":[63],"LLMs":[64],"on":[65],"curated":[66],"datasets":[67],"integrate":[69],"YARA":[70],"rules,":[71],"GitHub":[72],"Security":[73],"Advisories,":[74],"code":[77],"snippets":[78],"with":[79],"aim":[81],"enhancing":[83],"classification":[84],"accuracy.":[85,111],"came":[87],"across":[88],"a":[89,109],"counterintuitive":[90],"outcome:":[91],"While":[92],"RAG":[93,137],"is":[94,116],"expected":[95],"boost":[97],"up":[98],"prediction":[100],"performance,":[101],"it":[102,120],"fails":[103],"performed":[106],"evaluation,":[107],"obtaining":[108],"mediocre":[110],"contrast,":[113],"more":[117],"effective":[118],"significantly":[121],"improves":[122],"code,":[127],"achieving":[128],"97%":[129],"accuracy":[130],"95%":[132],"balanced":[133],"accuracy,":[134],"outperforming":[135],"approaches.":[138],"Thus,":[139],"future":[140],"work":[141],"should":[142],"expand":[143],"knowledge":[145],"bases,":[146],"refine":[147],"retrieval":[148],"models,":[149],"explore":[151],"hybrid":[152],"AI-driven":[153],"cybersecurity":[154],"solutions.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-24T00:00:00"}
