{"id":"https://openalex.org/W4385570951","doi":"https://doi.org/10.18653/v1/2023.findings-acl.678","title":"Understanding Programs by Exploiting (Fuzzing) Test Cases","display_name":"Understanding Programs by Exploiting (Fuzzing) Test Cases","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570951","doi":"https://doi.org/10.18653/v1/2023.findings-acl.678"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-acl.678","doi":"https://doi.org/10.18653/v1/2023.findings-acl.678","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.678","pdf_url":"https://aclanthology.org/2023.findings-acl.678.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-acl.678.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101372177","display_name":"Jianyu Zhao","orcid":"https://orcid.org/0009-0000-9812-2046","observed_orcids":["https://orcid.org/0009-0000-9812-2046"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Zhao","raw_affiliation_strings":["Tencent Security Big Data Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Security Big Data Lab ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113114882","display_name":"Yuyang Rong","orcid":"https://orcid.org/0000-0003-0648-0255","observed_orcids":["https://orcid.org/0000-0003-0648-0255"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyang Rong","raw_affiliation_strings":["UC Davis ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis ,","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067005644","display_name":"Yiwen Guo","orcid":"https://orcid.org/0000-0002-0709-4877","observed_orcids":["https://orcid.org/0000-0002-0709-4877"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiwen Guo","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101316564","display_name":"Yifeng He","orcid":"https://orcid.org/0000-0002-5389-7128","observed_orcids":["https://orcid.org/0000-0002-5389-7128"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifeng He","raw_affiliation_strings":["UC Davis ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis ,","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100353681","display_name":"Hao Chen","orcid":"https://orcid.org/0009-0008-9029-8571","observed_orcids":["https://orcid.org/0009-0008-9029-8571"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["UC Davis ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis ,","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3013,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97090987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10667","last_page":"10679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.00019999999494757503,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/program-comprehension","display_name":"program comprehension","score":0.7379999756813049},{"id":"https://openalex.org/keywords/fuzzing","display_name":"fuzzing","score":0.6869999766349792},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.878000020980835},{"id":"https://openalex.org/keywords/code-representation-learning","display_name":"code representation learning","score":0.8659999966621399},{"id":"https://openalex.org/keywords/code-clone-detection","display_name":"code clone detection","score":0.8209999799728394},{"id":"https://openalex.org/keywords/code-classification","display_name":"code classification","score":0.9980000257492065},{"id":"https://openalex.org/keywords/input-output-relationship","display_name":"input-output relationship","score":0.640999972820282},{"id":"https://openalex.org/keywords/programming-language-semantics","display_name":"program semantics","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550819754600525},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.8238725662231445},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.8082029819488525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6231710910797119},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5671648979187012},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5431330800056458},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5045017004013062},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.49788618087768555},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4903130829334259},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.48574262857437134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641263484954834},{"id":"https://openalex.org/C67463725","wikidata":"https://www.wikidata.org/wiki/Q17081452","display_name":"Natural language programming","level":5,"score":0.4304811954498291},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4279497265815735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3945879638195038},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1335371434688568},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.12820780277252197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.12477648258209229},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.findings-acl.678","doi":"https://doi.org/10.18653/v1/2023.findings-acl.678","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.678","pdf_url":"https://aclanthology.org/2023.findings-acl.678.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.13592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.13592","pdf_url":"https://arxiv.org/pdf/2305.13592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2305.13592","doi":"https://doi.org/10.48550/arxiv.2305.13592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.13592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-acl.678","doi":"https://doi.org/10.18653/v1/2023.findings-acl.678","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.678","pdf_url":"https://aclanthology.org/2023.findings-acl.678.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3376968242","display_name":"SaTC: CORE: Medium: Collaborative: Towards Robust Machine Learning Systems","funder_award_id":"1801751","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8146942196","display_name":"SaTC: CORE: Small: Collaborative: Understanding and Detecting Memory Bugs in Rust","funder_award_id":"1956364","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385570951.pdf","grobid_xml":"https://content.openalex.org/works/W4385570951.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2971869958","https://openalex.org/W3008088841","https://openalex.org/W3013302896","https://openalex.org/W3086007799","https://openalex.org/W3126675481","https://openalex.org/W3170092793","https://openalex.org/W3198188208","https://openalex.org/W3198685994","https://openalex.org/W4299358159","https://openalex.org/W4384302803","https://openalex.org/W4389438938","https://openalex.org/W4394664141"],"related_works":["https://openalex.org/W4404783874","https://openalex.org/W7141484058","https://openalex.org/W4411300610","https://openalex.org/W4411446194","https://openalex.org/W4406887040","https://openalex.org/W4407759429","https://openalex.org/W4414787381","https://openalex.org/W4415620282","https://openalex.org/W4377164434","https://openalex.org/W7215073738"],"abstract_inverted_index":{"Semantic":[0],"understanding":[1,120,154,173],"of":[2,14,35,43,81,121,133,136,152,164],"programs":[3,46,66],"has":[4,25],"attracted":[5],"great":[6],"attention":[7],"in":[8,19,54],"the":[9,97,101,131,137,150,165],"community.Inspired":[10],"by":[11,28,187],"recent":[12],"successes":[13],"large":[15,188],"language":[16,21,31,37],"models":[17],"(LLMs)":[18],"natural":[20,36],"understanding,":[22],"tremendous":[23],"progress":[24],"been":[26],"made":[27],"treating":[29],"programming":[30],"as":[32,103],"another":[33],"sort":[34],"and":[38,63,67,73,93,99,144,155,179,182],"training":[39],"LLMs":[40],"on":[41,170],"corpora":[42],"program":[44,102,153,172],"code.However,":[45],"are":[47,59,75,126],"essentially":[48],"different":[49,88],"from":[50],"texts":[51],"after":[52],"all,":[53],"a":[55,79,104,111,117,160],"sense":[56],"that":[57,125],"they":[58],"normally":[60],"heavily":[61],"structured":[62],"syntax-strict.In":[64],"particular,":[65],"their":[68],"basic":[69],"units":[70],"(i.e.,":[71],"functions":[72],"subroutines)":[74],"designed":[76],"to":[77,108,129,141,148],"demonstrate":[78],"variety":[80],"behaviors":[82],"and/or":[83],"provide":[84],"possible":[85,94],"outputs,":[86],"given":[87,159],"inputs.The":[89],"relationship":[90,112],"between":[91],"inputs":[92,124],"outputs/behaviors":[95],"represents":[96],"functions/subroutines":[98],"profiles":[100],"whole.Therefore,":[105],"we":[106,139],"propose":[107,145],"incorporate":[109],"such":[110],"into":[113],"learning,":[114,158],"for":[115],"achieving":[116],"deeper":[118],"semantic":[119],"programs.To":[122],"obtain":[123],"representative":[127],"enough":[128],"trigger":[130],"execution":[132],"most":[134],"part":[135],"code,":[138],"resort":[140],"fuzz":[142,146],"testing":[143],"tuning":[147],"boost":[149],"performance":[151],"code":[156,176,180],"representation":[157],"pre-trained":[161],"LLM.The":[162],"effectiveness":[163],"proposed":[166],"method":[167],"is":[168,190],"verified":[169],"two":[171],"tasks":[174],"including":[175],"clone":[177],"detection":[178],"classification,":[181],"it":[183],"outperforms":[184],"current":[185],"state-of-the-arts":[186],"margins.Code":[189],"available":[191],"at":[192],"https:":[193],"//github.com/rabbitjy/FuzzTuning.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-08-05T00:00:00"}