{"id":"https://openalex.org/W4415746195","doi":"https://doi.org/10.1109/icsme64153.2025.00089","title":"Detecting Adversarial Prompted AI-Generated Code on Stack Overflow: A Benchmark Dataset and an Enhanced Detection Approach","display_name":"Detecting Adversarial Prompted AI-Generated Code on Stack Overflow: A Benchmark Dataset and an Enhanced Detection Approach","publication_year":2025,"publication_date":"2025-09-07","ids":{"openalex":"https://openalex.org/W4415746195","doi":"https://doi.org/10.1109/icsme64153.2025.00089"},"language":null,"primary_location":{"id":"doi:10.1109/icsme64153.2025.00089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsme64153.2025.00089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Maintenance and Evolution (ICSME)","raw_type":"proceedings-article"},"type":"article","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/A5084068350","display_name":"Aman Swaraj","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aman Swaraj","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111006775","display_name":"Krishna Kant Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishna Agarwal","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Atharv Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Atharv Joshi","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633096","display_name":"Sandeep Kumar","orcid":"https://orcid.org/0000-0003-0747-6776"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeep Kumar","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Department of Computer Science and Engineering,India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084068350"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44491935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"839","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.5005999803543091,"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/T10260","display_name":"Software Engineering Research","score":0.5005999803543091,"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":0.14350000023841858,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.061900001019239426,"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/code","display_name":"Code (set theory)","score":0.7407000064849854},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6841999888420105},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5771999955177307},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5716999769210815},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.527400016784668},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.46549999713897705},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.4323999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764000296592712},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7407000064849854},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.3433000147342682},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsme64153.2025.00089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsme64153.2025.00089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Maintenance and Evolution (ICSME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2008056655","https://openalex.org/W2295598076","https://openalex.org/W2581748289","https://openalex.org/W2911964244","https://openalex.org/W3037862795","https://openalex.org/W3098605233","https://openalex.org/W4379259169","https://openalex.org/W4388858772","https://openalex.org/W4388954848","https://openalex.org/W4391282616","https://openalex.org/W4393157398","https://openalex.org/W4394828356","https://openalex.org/W4394859329","https://openalex.org/W4398766125","https://openalex.org/W4400582732","https://openalex.org/W4404541495","https://openalex.org/W4406867827","https://openalex.org/W4410552802","https://openalex.org/W4410552935"],"related_works":[],"abstract_inverted_index":{"AI-generated":[0,41],"code":[1,49,57,86,127,166,170,202,208],"has":[2],"become":[3],"an":[4,159],"integral":[5],"part":[6],"of":[7,107,117,165,200],"the":[8,169,198],"mainstream":[9],"developer":[10],"workflow":[11],"today.":[12],"However,":[13],"in":[14,78],"community-driven":[15],"platforms":[16],"like":[17],"Stack":[18],"Overflow":[19],"(SO),":[20],"where":[21],"trust,":[22],"authorship,":[23],"and":[24,53,64,66,109,180,207],"credibility":[25],"are":[26,61],"important,":[27],"it":[28],"can":[29],"lead":[30],"to":[31,89,149,154,183],"serious":[32],"complications.":[33],"While":[34],"recent":[35],"studies":[36,80],"have":[37,44,98],"focused":[38],"on":[39,59,143],"detecting":[40],"code,":[42],"they":[43],"mostly":[45],"worked":[46],"with":[47,113,168,204],"long":[48],"samples":[50],"from":[51],"repositories":[52],"assignments.":[54],"In":[55],"contrast,":[56],"snippets":[58],"SO":[60,108],"often":[62],"small":[63],"context-specific,":[65],"thus":[67],"may":[68],"prove":[69],"more":[70],"challenging":[71],"for":[72,193],"detection.":[73],"Moreover,":[74],"another":[75],"aspect":[76],"overlooked":[77],"prior":[79],"concerns":[81],"recognizing":[82],"adversarially":[83,119],"prompted":[84,120,185],"AI":[85,121,145,201],"deliberately":[87],"crafted":[88],"resemble":[90],"human-written":[91],"code.":[92,186],"To":[93],"address":[94],"these":[95],"limitations,":[96],"we":[97,124,157],"first":[99],"introduced":[100],"a":[101,114],"large-scale":[102],"dataset":[103],"comprising":[104],"3500":[105],"pairs":[106],"ChatGPT":[110],"answers,":[111],"along":[112,167],"curated":[115,133],"set":[116],"4500":[118],"responses.":[122],"Next,":[123],"evaluate":[125],"existing":[126,139],"language":[128],"models":[129,140,179],"over":[130],"this":[131],"newly":[132],"dataset.":[134],"Our":[135,172,187],"evaluation":[136],"shows":[137,174],"that":[138],"perform":[141],"well":[142],"standard":[144],"answers":[146],"but":[147],"fail":[148],"detect":[150],"adversarial":[151,184,205],"ones.":[152],"Finally,":[153],"improve":[155],"detection,":[156],"propose":[158],"ensemble":[160],"approach":[161,173],"combining":[162],"stylometric":[163],"features":[164],"embeddings.":[171],"consistent":[175],"improvements":[176],"across":[177],"multiple":[178],"improves":[181],"resistance":[182],"overall":[188],"findings":[189],"open":[190],"promising":[191],"directions":[192],"future":[194],"research":[195],"into":[196],"understanding":[197],"nuances":[199],"detection":[203],"prompting":[206],"stylometry.":[209]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-31T00:00:00"}