{"id":"https://openalex.org/W7166822288","doi":"https://doi.org/10.18653/v1/2026.acl-long.108","title":"CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions","display_name":"CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166822288","doi":"https://doi.org/10.18653/v1/2026.acl-long.108"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.108","pdf_url":"https://aclanthology.org/2026.acl-long.108.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.108.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126788842","display_name":"Jingwei Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwei Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139720227","display_name":"Xinxiang Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinxiang Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139753553","display_name":"Jing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126786657","display_name":"Shengyu Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyu Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139724823","display_name":"Jinman Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinman Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78200253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2352","last_page":"2382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7394000291824341,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7394000291824341,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.05050000175833702,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.04320000112056732,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/test","display_name":"Test (biology)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.336899995803833},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.2840000092983246},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2775000035762787},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2623000144958496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5885000228881836},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23919999599456787},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2378000020980835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.108","pdf_url":"https://aclanthology.org/2026.acl-long.108.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.108","pdf_url":"https://aclanthology.org/2026.acl-long.108.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166822288.pdf","grobid_xml":"https://content.openalex.org/works/W7166822288.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"evaluation":[1],"of":[2,17,87,123,147],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"for":[7,25],"code":[8,80],"generation":[9],"relies":[10],"heavily":[11],"on":[12,150],"the":[13,58,83,96,118,145],"quality":[14],"and":[15,74,85,103],"robustness":[16],"test":[18,49],"cases.However,":[19],"existing":[20,124],"benchmarks":[21,151],"often":[22],"lack":[23],"coverage":[24],"subtle":[26],"corner":[27],"cases,":[28],"allowing":[29],"incorrect":[30,129],"solutions":[31,130],"to":[32,45,77,139],"pass.To":[33],"bridge":[34],"this":[35],"gap,":[36],"we":[37,90],"propose":[38],"CodeHacker,":[39],"an":[40],"automated":[41],"agent":[42,97],"framework":[43],"dedicated":[44],"generating":[46],"targeted":[47],"adversarial":[48,107,136],"cases":[50,137],"that":[51,114,131],"expose":[52],"latent":[53],"vulnerabilities":[54],"in":[55,61],"program":[56],"submissions.Mimicking":[57],"hack":[59],"mechanism":[60],"competitive":[62],"programming,":[63],"CodeHacker":[64,115],"employs":[65],"a":[66,92],"multistrategy":[67],"approach,":[68],"including":[69],"stress":[70],"testing,":[71],"anti-hash":[72],"attacks,":[73,89],"logic-specific":[75],"targeting":[76],"break":[78],"specific":[79],"submissions.To":[81],"ensure":[82],"validity":[84],"reliability":[86],"these":[88],"introduce":[91],"Calibration":[93],"Phase,":[94],"where":[95],"iteratively":[98],"refines":[99],"its":[100],"own":[101],"Validator":[102],"Checker":[104],"via":[105],"self-generated":[106],"probes":[108],"before":[109],"evaluating":[110],"contestant":[111],"code.Experiments":[112],"demonstrate":[113],"significantly":[116],"improves":[117],"True":[119],"Negative":[120],"Rate":[121],"(TNR)":[122],"datasets,":[125],"effectively":[126],"filtering":[127],"out":[128],"were":[132],"previously":[133],"accepted.Furthermore,":[134],"generated":[135],"prove":[138],"be":[140],"superior":[141],"training":[142],"data,":[143],"boosting":[144],"performance":[146],"RL-trained":[148],"models":[149],"like":[152],"LiveCodeBench.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
