{"id":"https://openalex.org/W4403536243","doi":"https://doi.org/10.1145/3691620.3695539","title":"Coding-PTMs: How to Find Optimal Code Pre-trained Models for Code Embedding in Vulnerability Detection?","display_name":"Coding-PTMs: How to Find Optimal Code Pre-trained Models for Code Embedding in Vulnerability Detection?","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403536243","doi":"https://doi.org/10.1145/3691620.3695539"},"language":"en","primary_location":{"id":"doi:10.1145/3691620.3695539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691620.3695539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091563572","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0001-7776-3178"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-7776-3178","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027202117","display_name":"Lina Gong","orcid":"https://orcid.org/0000-0002-5272-6706"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Gong","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-5272-6706","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025184050","display_name":"Zhiqiu Huang","orcid":"https://orcid.org/0000-0001-6843-1892"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiu Huang","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-6843-1892","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664076","display_name":"Yongwei Wang","orcid":"https://orcid.org/0000-0001-9712-8964"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Wang","raw_affiliation_strings":["Shanghai Institute for Advanced Study and College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9712-8964","affiliations":[{"raw_affiliation_string":"Shanghai Institute for Advanced Study and College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051555459","display_name":"Mingqiang Wei","orcid":"https://orcid.org/0000-0003-0429-490X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqiang Wei","raw_affiliation_strings":["School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-0429-490X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Key Laboratory of Safety-Critical Software, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-8807","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1732","last_page":"1744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.706560492515564},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6386451125144958},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6303092241287231},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5960320234298706},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.552180826663971},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.4258705675601959},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2850632667541504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2467566728591919},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.21004778146743774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10484668612480164},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08139786124229431}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706560492515564},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6386451125144958},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6303092241287231},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5960320234298706},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.552180826663971},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.4258705675601959},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2850632667541504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2467566728591919},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.21004778146743774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10484668612480164},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08139786124229431},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3691620.3695539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691620.3695539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3734283955","display_name":null,"funder_award_id":"NJ2024029","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G437908683","display_name":null,"funder_award_id":"BK20220881","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5473515455","display_name":null,"funder_award_id":"U2241216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7809263010","display_name":null,"funder_award_id":"62202223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1953529280","https://openalex.org/W2029123435","https://openalex.org/W2099919734","https://openalex.org/W2158864412","https://openalex.org/W2250539671","https://openalex.org/W2510885373","https://openalex.org/W2560674852","https://openalex.org/W2605961645","https://openalex.org/W2747329762","https://openalex.org/W2781491433","https://openalex.org/W2887202723","https://openalex.org/W2888329843","https://openalex.org/W2946417913","https://openalex.org/W2953606244","https://openalex.org/W2963341956","https://openalex.org/W2963548617","https://openalex.org/W2964150020","https://openalex.org/W2964183261","https://openalex.org/W2994865335","https://openalex.org/W3011013751","https://openalex.org/W3033393716","https://openalex.org/W3033777149","https://openalex.org/W3034938700","https://openalex.org/W3039695075","https://openalex.org/W3046757114","https://openalex.org/W3084812981","https://openalex.org/W3101228802","https://openalex.org/W3102466593","https://openalex.org/W3105867435","https://openalex.org/W3127782461","https://openalex.org/W3127971289","https://openalex.org/W3166095789","https://openalex.org/W3198685994","https://openalex.org/W3203041411","https://openalex.org/W3217001695","https://openalex.org/W4207063495","https://openalex.org/W4213007905","https://openalex.org/W4221061332","https://openalex.org/W4221153183","https://openalex.org/W4281763794","https://openalex.org/W4285490477","https://openalex.org/W4285490489","https://openalex.org/W4292491372","https://openalex.org/W4312465319","https://openalex.org/W4312757223","https://openalex.org/W4313137049","https://openalex.org/W4318562265","https://openalex.org/W4320235690","https://openalex.org/W4378347255","https://openalex.org/W4380763529","https://openalex.org/W4385967654","https://openalex.org/W4387298393","https://openalex.org/W4389523928","https://openalex.org/W4390640589"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2955990109","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W4311138500","https://openalex.org/W2017266518","https://openalex.org/W2419146053"],"abstract_inverted_index":{"Vulnerability":[0],"detection":[1,201,282],"is":[2,48,99,129],"garnering":[3],"increasing":[4],"attention":[5],"in":[6,37,192,279],"software":[7],"engineering,":[8],"since":[9],"code":[10,19,31,51,79,85,105,110,144,149,168,195,207,222,242,261,266,274,277],"vulnerabilities":[11],"possibly":[12],"pose":[13],"significant":[14],"security.":[15],"Recently,":[16],"reusing":[17],"various":[18,109,148],"pre-trained":[20,45],"models":[21,46],"(e.g.,":[22],"CodeBERT,":[23],"CodeT5,":[24],"and":[25,93,117,126,139,164,177,216,238,271],"CodeGen)":[26],"has":[27],"become":[28],"common":[29],"for":[30,42,197,218,276],"embedding":[32,80,106,120,127,145,169,208,278],"without":[33],"providing":[34],"reasonable":[35],"justifications":[36],"vulnerability":[38,91,200,281],"detection.":[39],"The":[40],"premise":[41],"casually":[43],"utilizing":[44],"(PTMs)":[47],"that":[49,66,98,104],"the":[50,63,76,88,95,115,135,141,153,161,240,245,258,269],"embeddings":[52,262],"generated":[53,81,107,146,170,263],"by":[54,82,108,147,171,264],"different":[55,84,172],"PTMs":[56,86,111,150,173,196,243,267,275],"would":[57],"generate":[58],"a":[59,186,220,229,235],"similar":[60],"impact":[61],"on":[62,87,123,180,268],"performance.":[64],"Is":[65],"TRUE?":[67],"To":[68,155],"answer":[69],"this":[70,157],"important":[71],"question,":[72],"we":[73,159,183,204],"systematically":[74],"investigate":[75],"effects":[77],"of":[78,90,137,143,167,260],"ten":[83],"performance":[89,116,270],"detection,":[92],"get":[94],"answer,":[96],"i.e.,":[97],"NOT":[100],"true.":[101],"We":[102,226,249],"observe":[103],"can":[112],"indeed":[113],"influence":[114],"selecting":[118,193],"an":[119],"technique":[121],"based":[122],"parameter":[124],"scales":[125],"dimension":[128],"not":[130],"reliable.":[131],"Our":[132],"findings":[133],"highlight":[134],"necessity":[136],"quantifying":[138],"evaluating":[140],"characteristics":[142,259],"to":[151,174,189,233,252,256],"understand":[152],"effects.":[154],"achieve":[156],"goal,":[158],"analyze":[160],"numerical":[162],"representation":[163],"data":[165],"distribution":[166],"evaluate":[175,257],"differences":[176],"characteristics.":[178],"Based":[179],"these":[181],"insights,":[182],"propose":[184],"Coding-PTMs,":[185],"recommendation":[187,224,236],"framework":[188],"assist":[190],"engineers":[191,251],"optimal":[194,241,273],"their":[198,280],"specific":[199],"tasks.":[202,283],"Specifically,":[203],"define":[205],"thirteen":[206],"metrics":[209],"across":[210],"three":[211],"dimensions":[212],"(i.e.,":[213],"statistics,":[214],"norm,":[215],"distribution)":[217],"constructing":[219],"specialized":[221],"PTM":[223],"dataset.":[225],"then":[227],"employ":[228],"Random":[230],"Forest":[231],"classifier":[232],"train":[234],"model":[237,247],"identify":[239],"from":[244],"candidate":[246,265],"zoo.":[248],"encourage":[250],"use":[253],"our":[254],"Coding-PTMs":[255],"recommend":[272]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}