{"id":"https://openalex.org/W4388229767","doi":"https://doi.org/10.1145/3630008","title":"Poison Attack and Poison Detection on Deep Source Code Processing Models","display_name":"Poison Attack and Poison Detection on Deep Source Code Processing Models","publication_year":2023,"publication_date":"2023-11-02","ids":{"openalex":"https://openalex.org/W4388229767","doi":"https://doi.org/10.1145/3630008"},"language":"en","primary_location":{"id":"doi:10.1145/3630008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630008","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-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/A5100405693","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-5579-8852"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li \u2642","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5579-8852","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448023","display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-0198-2304"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Li","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0198-2304","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008116021","display_name":"Huangzhao Zhang","orcid":"https://orcid.org/0000-0002-0324-4591"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huangzhao Zhang","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0324-4591","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447682","display_name":"Ge Li","orcid":"https://orcid.org/0000-0002-5828-0186"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5828-0186","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049100391","display_name":"Zhi Jin","orcid":"https://orcid.org/0000-0003-1087-226X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Jin","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1087-226X","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047688641","display_name":"Xing Hu","orcid":"https://orcid.org/0000-0003-0093-3292"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"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":"Xing Hu","raw_affiliation_strings":["Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0003-0093-3292","affiliations":[{"raw_affiliation_string":"Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xia","raw_affiliation_strings":["Huawei, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6302-3256","affiliations":[{"raw_affiliation_string":"Huawei, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9211,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.98115937,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":"3","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9984999895095825,"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/T11424","display_name":"Security and Verification in Computing","score":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.8260921835899353},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6813893914222717},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.6310404539108276},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5335417985916138},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.521111786365509},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.47236400842666626},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4515884220600128},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.4181622266769409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3501342535018921},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12068116664886475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260921835899353},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6813893914222717},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6310404539108276},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5335417985916138},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.521111786365509},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.47236400842666626},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4515884220600128},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4181622266769409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3501342535018921},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12068116664886475},{"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:10.1145/3630008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630008","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1884936576","display_name":null,"funder_award_id":"61832009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3446613798","display_name":null,"funder_award_id":"62192730","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5393181860","display_name":"\u9762\u5411\u7a0b\u5e8f\u7406\u89e3\u7684\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\u53ca\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5482656022","display_name":null,"funder_award_id":"62192731","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8449925957","display_name":null,"funder_award_id":"62192733","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8982337699","display_name":null,"funder_award_id":"62072007, 62192733, 61832009, 62192731, 62152730, 62192730","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1520914943","https://openalex.org/W1832693441","https://openalex.org/W1969031936","https://openalex.org/W2064675550","https://openalex.org/W2065053490","https://openalex.org/W2109943392","https://openalex.org/W2189153846","https://openalex.org/W2308618763","https://openalex.org/W2511803001","https://openalex.org/W2605202003","https://openalex.org/W2727832342","https://openalex.org/W2741705590","https://openalex.org/W2747329762","https://openalex.org/W2748789698","https://openalex.org/W2795753518","https://openalex.org/W2796004214","https://openalex.org/W2884276923","https://openalex.org/W2885030880","https://openalex.org/W2888328667","https://openalex.org/W2897865027","https://openalex.org/W2907705732","https://openalex.org/W2955426500","https://openalex.org/W2963888996","https://openalex.org/W2963935794","https://openalex.org/W2970335439","https://openalex.org/W2972082064","https://openalex.org/W2973529529","https://openalex.org/W2990270730","https://openalex.org/W2997451752","https://openalex.org/W3005628256","https://openalex.org/W3011564318","https://openalex.org/W3012113073","https://openalex.org/W3014339000","https://openalex.org/W3035367371","https://openalex.org/W3043789969","https://openalex.org/W3081159607","https://openalex.org/W3083185154","https://openalex.org/W3101118213","https://openalex.org/W3105903381","https://openalex.org/W3106646114","https://openalex.org/W3109409894","https://openalex.org/W3109966548","https://openalex.org/W3111602563","https://openalex.org/W3129468510","https://openalex.org/W3134686229","https://openalex.org/W3135766489","https://openalex.org/W3154734736","https://openalex.org/W3161027892","https://openalex.org/W3161071537","https://openalex.org/W3163168187","https://openalex.org/W3173784240","https://openalex.org/W3175052694","https://openalex.org/W3176270593","https://openalex.org/W3178326529","https://openalex.org/W3182763642","https://openalex.org/W3193682477","https://openalex.org/W3212213895","https://openalex.org/W3215670835","https://openalex.org/W4205371973","https://openalex.org/W4206238733","https://openalex.org/W4253813365","https://openalex.org/W4294560978","https://openalex.org/W4298140072","https://openalex.org/W4308627220","https://openalex.org/W4313913687","https://openalex.org/W4362508616","https://openalex.org/W4376312043","https://openalex.org/W4377238789","https://openalex.org/W4384345649","https://openalex.org/W4394638297","https://openalex.org/W6739088070"],"related_works":["https://openalex.org/W2344367508","https://openalex.org/W2571988079","https://openalex.org/W2098629748","https://openalex.org/W2144528247","https://openalex.org/W4244608052","https://openalex.org/W4312050194","https://openalex.org/W2147884840","https://openalex.org/W4360981376","https://openalex.org/W3188088379","https://openalex.org/W2997255751"],"abstract_inverted_index":{"In":[0],"the":[1,24,62,114,159,188,264,282],"software":[2],"engineering":[3],"(SE)":[4],"community,":[5],"deep":[6,117,152,198,236],"learning":[7],"(DL)":[8],"has":[9],"recently":[10],"been":[11],"applied":[12],"to":[13,23,43,53,93,109,122,196,245],"many":[14],"source":[15,118,132,153,199,237],"code":[16,119,133,154,200,209,238],"processing":[17,120,155,201,239],"tasks,":[18],"achieving":[19],"state-of-the-art":[20],"results.":[21],"Due":[22],"poor":[25],"interpretability":[26],"of":[27,116,284],"DL":[28,44,58],"models,":[29,45,202],"their":[30],"security":[31,41],"vulnerabilities":[32],"require":[33],"scrutiny.":[34],"Recently,":[35],"researchers":[36,274],"have":[37,241],"identified":[38],"an":[39,173],"emergent":[40],"threat":[42],"namely,":[46],"poison":[47,66,123,128,147,163,168,175,185,220,246,254,261,278],"attacks":[48,221,279],".":[49,180],"The":[50,68,212],"attackers":[51,96],"aim":[52],"inject":[54],"insidious":[55],"backdoors":[56,69],"into":[57],"models":[59,73,100,121,156,240],"by":[60,157,257],"poisoning":[61,158],"training":[63,160,189,265],"data":[64,161],"with":[65,76,84,87,162,222],"samples.":[67,164],"mean":[70],"that":[71,215,234],"poisoned":[72,99],"work":[74,270],"normally":[75],"clean":[77],"inputs":[78,85],"but":[79],"produce":[80,143],"targeted":[81],"erroneous":[82],"results":[83,213],"embedded":[86],"specific":[88],"triggers.":[89],"By":[90],"using":[91],"triggers":[92],"activate":[94],"backdoors,":[95],"can":[97,142,182,271],"manipulate":[98],"in":[101,187,263],"security-related":[102],"scenarios":[103],"(e.g.,":[104],"defect":[105,204],"detection)":[106],"and":[107,145,149,194,208,275,280],"lead":[108],"severe":[110],"consequences.":[111],"To":[112,165],"verify":[113],"vulnerability":[115,244],"attacks,":[124,169],"we":[125,170],"present":[126],"a":[127,137,223,242],"attack":[129,151,225,255],"approach":[130,177],"for":[131],"named":[134,178],"CodePoisoner":[135,141,193,217],"as":[136],"strong":[138,243],"imaginary":[139],"enemy.":[140],"compilable":[144],"functionality-preserving":[146],"samples":[148,186,262],"effectively":[150,250],"defend":[166],"against":[167,252],"further":[171],"propose":[172],"effective":[174],"detection":[176],"CodeDetector":[179,181,195,249],"automatically":[183],"identify":[184],"data.":[190,266],"We":[191,267],"apply":[192],"six":[197],"including":[203],"detection,":[205,207],"clone":[206],"repair":[210],"models.":[211],"show":[214],"\u2776":[216],"conducts":[218],"successful":[219],"high":[224],"success":[226],"rate":[227],"(average:":[228],"98.3%,":[229],"maximum:":[230],"100%).":[231],"It":[232],"validates":[233],"existing":[235],"attacks.":[247],"\u2777":[248],"defends":[251],"multiple":[253],"approaches":[256],"detecting":[258],"(maximum:":[259],"100%)":[260],"hope":[268],"this":[269],"help":[272],"SE":[273],"practitioners":[276],"notice":[277],"inspire":[281],"design":[283],"more":[285],"advanced":[286],"defense":[287],"techniques.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}