{"id":"https://openalex.org/W4408248601","doi":"https://doi.org/10.1145/3721977","title":"A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Tasks","display_name":"A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Tasks","publication_year":2025,"publication_date":"2025-03-05","ids":{"openalex":"https://openalex.org/W4408248601","doi":"https://doi.org/10.1145/3721977"},"language":"en","primary_location":{"id":"doi:10.1145/3721977","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721977","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721977","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"review","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721977","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003772299","display_name":"Beatrice Casey","orcid":"https://orcid.org/0009-0001-0097-2120"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beatrice Casey","raw_affiliation_strings":["University of Notre Dame, Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043541139","display_name":"Joanna C. S. Santos","orcid":"https://orcid.org/0000-0001-8743-2516"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joanna C. S. Santos","raw_affiliation_strings":["University of Notre Dame, Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064483259","display_name":"George Perry","orcid":"https://orcid.org/0009-0002-8438-5210"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Perry","raw_affiliation_strings":["University of Notre Dame, Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003772299"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":40.5598,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99707252,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"57","issue":"8","first_page":"1","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9984999895095825,"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":0.8882864713668823},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5458236336708069},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5349463224411011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258001685142517},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4949340224266052},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49024897813796997},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4836786687374115},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4710630774497986},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.45047104358673096},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4486461281776428},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4442431330680847},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4242647588253021},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3868715763092041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36233216524124146},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35726198554039},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.302356481552124},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.21075916290283203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882864713668823},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5458236336708069},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5349463224411011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258001685142517},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4949340224266052},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49024897813796997},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4836786687374115},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4710630774497986},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.45047104358673096},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4486461281776428},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4442431330680847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4242647588253021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3868715763092041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36233216524124146},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35726198554039},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.302356481552124},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.21075916290283203},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721977","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721977","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721977","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3721977","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721977","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721977","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408248601.pdf"},"referenced_works_count":192,"referenced_works":["https://openalex.org/W121173099","https://openalex.org/W572872720","https://openalex.org/W1562934601","https://openalex.org/W1605152326","https://openalex.org/W1992114977","https://openalex.org/W2004758929","https://openalex.org/W2008857097","https://openalex.org/W2010256880","https://openalex.org/W2025411198","https://openalex.org/W2027822753","https://openalex.org/W2027887391","https://openalex.org/W2038590360","https://openalex.org/W2053154970","https://openalex.org/W2069268700","https://openalex.org/W2078197322","https://openalex.org/W2079215333","https://openalex.org/W2079753286","https://openalex.org/W2117426803","https://openalex.org/W2117798902","https://openalex.org/W2122483144","https://openalex.org/W2136117679","https://openalex.org/W2144344516","https://openalex.org/W2150071393","https://openalex.org/W2158297335","https://openalex.org/W2162739315","https://openalex.org/W2162944805","https://openalex.org/W2168103835","https://openalex.org/W2170478581","https://openalex.org/W2293624369","https://openalex.org/W2297419069","https://openalex.org/W2511947018","https://openalex.org/W2587002069","https://openalex.org/W2592125937","https://openalex.org/W2606250847","https://openalex.org/W2737925311","https://openalex.org/W2748690817","https://openalex.org/W2765858138","https://openalex.org/W2770225980","https://openalex.org/W2783078595","https://openalex.org/W2789977456","https://openalex.org/W2796200341","https://openalex.org/W2808549504","https://openalex.org/W2885030880","https://openalex.org/W2887773459","https://openalex.org/W2892195839","https://openalex.org/W2896313538","https://openalex.org/W2897619937","https://openalex.org/W2901941771","https://openalex.org/W2902979785","https://openalex.org/W2904727310","https://openalex.org/W2907778768","https://openalex.org/W2912899164","https://openalex.org/W2944264045","https://openalex.org/W2953482317","https://openalex.org/W2955082894","https://openalex.org/W2962960733","https://openalex.org/W2963208797","https://openalex.org/W2963250244","https://openalex.org/W2963784672","https://openalex.org/W2964136807","https://openalex.org/W2964150020","https://openalex.org/W2965861627","https://openalex.org/W2968904481","https://openalex.org/W2973109646","https://openalex.org/W2976184969","https://openalex.org/W2979183801","https://openalex.org/W2980966214","https://openalex.org/W2981328759","https://openalex.org/W2982577744","https://openalex.org/W2990323480","https://openalex.org/W2992636498","https://openalex.org/W2995824836","https://openalex.org/W2997640974","https://openalex.org/W2998879504","https://openalex.org/W2999058564","https://openalex.org/W3000032641","https://openalex.org/W3003472398","https://openalex.org/W3005065812","https://openalex.org/W3008371681","https://openalex.org/W3008406900","https://openalex.org/W3009129408","https://openalex.org/W3014780393","https://openalex.org/W3016970378","https://openalex.org/W3031273498","https://openalex.org/W3033777149","https://openalex.org/W3035568641","https://openalex.org/W3035733952","https://openalex.org/W3048901179","https://openalex.org/W3049398420","https://openalex.org/W3080279788","https://openalex.org/W3081867681","https://openalex.org/W3094130708","https://openalex.org/W3101228802","https://openalex.org/W3104849875","https://openalex.org/W3107289082","https://openalex.org/W3107793421","https://openalex.org/W3108563174","https://openalex.org/W3111397039","https://openalex.org/W3111602563","https://openalex.org/W3112782338","https://openalex.org/W3127782461","https://openalex.org/W3128948576","https://openalex.org/W3130200998","https://openalex.org/W3130630582","https://openalex.org/W3132728051","https://openalex.org/W3136874603","https://openalex.org/W3137781054","https://openalex.org/W3138019756","https://openalex.org/W3156393398","https://openalex.org/W3156480510","https://openalex.org/W3160246388","https://openalex.org/W3161071537","https://openalex.org/W3165214486","https://openalex.org/W3168383191","https://openalex.org/W3175658129","https://openalex.org/W3177413187","https://openalex.org/W3182763642","https://openalex.org/W3187025053","https://openalex.org/W3187454871","https://openalex.org/W3194346579","https://openalex.org/W3195612455","https://openalex.org/W3198619808","https://openalex.org/W3200595342","https://openalex.org/W3202579690","https://openalex.org/W3209432242","https://openalex.org/W3214973464","https://openalex.org/W3215377168","https://openalex.org/W4200192508","https://openalex.org/W4200620261","https://openalex.org/W4206078793","https://openalex.org/W4206660322","https://openalex.org/W4206908526","https://openalex.org/W4210469373","https://openalex.org/W4210493608","https://openalex.org/W4210788642","https://openalex.org/W4211027502","https://openalex.org/W4211181447","https://openalex.org/W4220908965","https://openalex.org/W4221150231","https://openalex.org/W4221153183","https://openalex.org/W4225484397","https://openalex.org/W4225673889","https://openalex.org/W4226057883","https://openalex.org/W4226247906","https://openalex.org/W4226416841","https://openalex.org/W4234535085","https://openalex.org/W4239751935","https://openalex.org/W4243607364","https://openalex.org/W4280493558","https://openalex.org/W4281396227","https://openalex.org/W4281641613","https://openalex.org/W4283212231","https://openalex.org/W4283646945","https://openalex.org/W4284664377","https://openalex.org/W4284667406","https://openalex.org/W4285490489","https://openalex.org/W4286331368","https://openalex.org/W4286454804","https://openalex.org/W4287848613","https://openalex.org/W4288269198","https://openalex.org/W4292982707","https://openalex.org/W4293201779","https://openalex.org/W4293451275","https://openalex.org/W4300405035","https://openalex.org/W4300878468","https://openalex.org/W4308641648","https://openalex.org/W4308653657","https://openalex.org/W4311012008","https://openalex.org/W4311165836","https://openalex.org/W4312298479","https://openalex.org/W4312326656","https://openalex.org/W4312436517","https://openalex.org/W4312690534","https://openalex.org/W4312727366","https://openalex.org/W4312742922","https://openalex.org/W4312757223","https://openalex.org/W4312817563","https://openalex.org/W4312969325","https://openalex.org/W4313121063","https://openalex.org/W4313563778","https://openalex.org/W4319587111","https://openalex.org/W4328027627","https://openalex.org/W4328028530","https://openalex.org/W4328028966","https://openalex.org/W4360996836","https://openalex.org/W4361792201","https://openalex.org/W4364297077","https://openalex.org/W4366771352","https://openalex.org/W4376606573","https://openalex.org/W4387298393","https://openalex.org/W4390679741","https://openalex.org/W4390679827"],"related_works":["https://openalex.org/W1988370859","https://openalex.org/W2613250302","https://openalex.org/W4294189394","https://openalex.org/W2124219668","https://openalex.org/W2095381028","https://openalex.org/W319507398","https://openalex.org/W2399811286","https://openalex.org/W4319867150","https://openalex.org/W2005927140","https://openalex.org/W4206294449"],"abstract_inverted_index":{"Machine":[0],"learning":[1,81],"techniques":[2,47,184],"for":[3,92],"cybersecurity-related":[4],"software":[5],"engineering":[6],"tasks":[7,95],"are":[8,106,117,131,142,193,204],"becoming":[9],"increasingly":[10],"popular.":[11],"The":[12],"representation":[13],"of":[14,21,37,45,58,77,88,104,122,149,161,198],"source":[15,39],"code":[16],"is":[17,31,51,68,154,172,179,185],"a":[18,75],"key":[19],"portion":[20],"the":[22,27,29,35,38,55,59,118,132,143,146,155,158,167,176,182,194,205],"technique":[23],"that":[24,114,166,178,190],"can":[25],"impact":[26],"way":[28],"model":[30,208],"able":[32],"to":[33,53,61],"learn":[34],"features":[36],"code.":[40],"With":[41],"an":[42],"increasing":[43],"number":[44],"these":[46,78],"being":[48],"developed,":[49],"it":[50],"valuable":[52],"see":[54],"current":[56],"state":[57],"field":[60],"better":[62],"understand":[63],"what":[64,67,86,102],"exists":[65],"and":[66,84,96,124,126,140,175,200],"not":[69],"there":[70],"yet.":[71],"This":[72],"article":[73],"presents":[74],"study":[76,101],"existing":[79],"machine":[80],"based":[82],"approaches":[83],"demonstrates":[85],"type":[87],"representations":[89,116,136,144,153],"were":[90],"used":[91,107],"different":[93,109],"cybersecurity":[94,170],"programming":[97],"languages.":[98],"Additionally,":[99],"we":[100,188],"types":[103],"models":[105,192],"with":[108,145,157],"representations.":[110],"We":[111,163],"have":[112],"found":[113,165,189],"graph-based":[115,152],"most":[119,134,168,183,195,206],"popular":[120,135,169,196,207],"category":[121,156,197],"representation,":[123],"tokenizers":[125,141],"Abstract":[127],"Syntax":[128],"Trees":[129],"(ASTs)":[130],"two":[133],"overall":[137],"(e.g.,":[138],"AST":[139],"highest":[147,159],"count":[148,160],"papers,":[150],"whereas":[151],"papers).":[162],"also":[164],"task":[171],"vulnerability":[173],"detection,":[174],"language":[177],"covered":[180],"by":[181],"C.":[186],"Finally,":[187],"sequence-based":[191],"models,":[199],"Support":[201],"Vector":[202],"Machines":[203],"overall.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}