{"id":"https://openalex.org/W3164461379","doi":"https://doi.org/10.1186/s42400-021-00088-4","title":"Bin2vec: learning representations of binary executable programs for security tasks","display_name":"Bin2vec: learning representations of binary executable programs for security tasks","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3164461379","doi":"https://doi.org/10.1186/s42400-021-00088-4","mag":"3164461379"},"language":"en","primary_location":{"id":"doi:10.1186/s42400-021-00088-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42400-021-00088-4","pdf_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-021-00088-4","source":{"id":"https://openalex.org/S3035238565","display_name":"Cybersecurity","issn_l":"2523-3246","issn":["2523-3246"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybersecurity","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-021-00088-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081720898","display_name":"Shushan Arakelyan","orcid":"https://orcid.org/0000-0002-4079-3952"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shushan Arakelyan","raw_affiliation_strings":["Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","Information Sciences Institute, Marina del Rey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, Marina del Rey, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039150275","display_name":"Sima Arasteh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sima Arasteh","raw_affiliation_strings":["Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","Information Sciences Institute, Marina del Rey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, Marina del Rey, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028735030","display_name":"Christophe Hauser","orcid":"https://orcid.org/0000-0001-7698-8041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Hauser","raw_affiliation_strings":["Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","Information Sciences Institute, Marina del Rey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, Marina del Rey, USA#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038964985","display_name":"Erik Kline","orcid":"https://orcid.org/0000-0003-0020-0056"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Kline","raw_affiliation_strings":["Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","Information Sciences Institute, Marina del Rey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, Marina del Rey, USA#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101715504","display_name":"Aram Galstyan","orcid":"https://orcid.org/0000-0003-4215-0886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aram Galstyan","raw_affiliation_strings":["Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","Information Sciences Institute, Marina del Rey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, 4676 Admiralty Way, Marina Del Rey, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Information Sciences Institute, Marina del Rey, USA#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081720898"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5677,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72079942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980000257492065,"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":0.9965000152587891,"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/executable","display_name":"Executable","score":0.852832019329071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252666592597961},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6814664006233215},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6009376049041748},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5845718383789062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49416807293891907},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.48052892088890076},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4675751030445099},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4339025318622589},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4313514232635498},{"id":"https://openalex.org/keywords/binary-decision-diagram","display_name":"Binary decision diagram","score":0.43013566732406616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35451143980026245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3458682596683502},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21893590688705444},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11662328243255615},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09186407923698425}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.852832019329071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252666592597961},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6814664006233215},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6009376049041748},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5845718383789062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49416807293891907},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.48052892088890076},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4675751030445099},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4339025318622589},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4313514232635498},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.43013566732406616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35451143980026245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3458682596683502},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21893590688705444},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11662328243255615},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09186407923698425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s42400-021-00088-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42400-021-00088-4","pdf_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-021-00088-4","source":{"id":"https://openalex.org/S3035238565","display_name":"Cybersecurity","issn_l":"2523-3246","issn":["2523-3246"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybersecurity","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2002.03388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03388","pdf_url":"https://arxiv.org/pdf/2002.03388","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3164461379","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.03388.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:2aa6f51b20e14fd0b9080cd2753e8870","is_oa":true,"landing_page_url":"https://doaj.org/article/2aa6f51b20e14fd0b9080cd2753e8870","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cybersecurity, Vol 4, Iss 1, Pp 1-14 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2002.03388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.03388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s42400-021-00088-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s42400-021-00088-4","pdf_url":"https://cybersecurity.springeropen.com/counter/pdf/10.1186/s42400-021-00088-4","source":{"id":"https://openalex.org/S3035238565","display_name":"Cybersecurity","issn_l":"2523-3246","issn":["2523-3246"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybersecurity","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308668","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164461379.pdf","grobid_xml":"https://content.openalex.org/works/W3164461379.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W192227941","https://openalex.org/W1584505081","https://openalex.org/W1761184020","https://openalex.org/W1771830246","https://openalex.org/W1943233084","https://openalex.org/W1992114977","https://openalex.org/W2000441200","https://openalex.org/W2025411198","https://openalex.org/W2036872500","https://openalex.org/W2113864883","https://openalex.org/W2153579005","https://openalex.org/W2154851992","https://openalex.org/W2282866165","https://openalex.org/W2289443514","https://openalex.org/W2294816372","https://openalex.org/W2297419069","https://openalex.org/W2298229910","https://openalex.org/W2301473744","https://openalex.org/W2344444819","https://openalex.org/W2511803001","https://openalex.org/W2514974017","https://openalex.org/W2532962075","https://openalex.org/W2557513839","https://openalex.org/W2558460151","https://openalex.org/W2577142429","https://openalex.org/W2749008552","https://openalex.org/W2765858138","https://openalex.org/W2789983203","https://openalex.org/W2809662498","https://openalex.org/W2886694146","https://openalex.org/W2892187814","https://openalex.org/W2926178846","https://openalex.org/W2949992015","https://openalex.org/W2950577311","https://openalex.org/W2963371736","https://openalex.org/W2963415211","https://openalex.org/W2963935794","https://openalex.org/W2968582201","https://openalex.org/W4229749093","https://openalex.org/W4300889023"],"related_works":["https://openalex.org/W3181292541","https://openalex.org/W3005238444","https://openalex.org/W3168622027","https://openalex.org/W2997915791","https://openalex.org/W2972316004","https://openalex.org/W2970862273","https://openalex.org/W2888698761","https://openalex.org/W2921355642","https://openalex.org/W3090891670","https://openalex.org/W2990761674","https://openalex.org/W3134050708","https://openalex.org/W2962961569","https://openalex.org/W3196620981","https://openalex.org/W3202507445","https://openalex.org/W3163086909","https://openalex.org/W3192984607","https://openalex.org/W3030854811","https://openalex.org/W3177441850","https://openalex.org/W3034880265","https://openalex.org/W3135395247"],"abstract_inverted_index":{"Abstract":[0],"Tackling":[1],"binary":[2,40,75,94,180],"program":[3,64],"analysis":[4,95],"problems":[5],"has":[6],"traditionally":[7],"implied":[8],"manually":[9],"defining":[10],"rules":[11],"and":[12,16,28,101,119,140],"heuristics,":[13],"a":[14,45,53,70,159],"tedious":[15],"time":[17],"consuming":[18],"task":[19],"for":[20,125,134,152],"human":[21],"analysts.":[22],"In":[23],"order":[24,67],"to":[25,44,68,89,109,171],"improve":[26],"automation":[27],"scalability,":[29],"we":[30],"propose":[31],"an":[32],"alternative":[33],"direction":[34],"based":[35,174],"on":[36,131,141,179],"distributed":[37],"representations":[38,88],"of":[39,47,74,82],"programs":[41],"with":[42,62],"applicability":[43],"number":[46],"downstream":[48],"tasks.":[49,127],"We":[50,78,104,128,157],"introduce":[51],"Bin2vec,":[52],"new":[54,160],"approach":[55,84,108],"leveraging":[56],"Graph":[57],"Convolutional":[58],"Networks":[59],"(GCN)":[60],"along":[61],"computational":[63],"graphs":[65],"in":[66,187,199],"learn":[69],"high":[71],"dimensional":[72],"representation":[73],"executable":[76],"programs.":[77],"demonstrate":[79,120],"the":[80,106,135,153,165,172],"versatility":[81],"this":[83],"by":[85,163,168],"using":[86],"our":[87,110,188,190],"solve":[90],"two":[91],"semantically":[92],"different":[93,143],"tasks":[96],"\u2013":[97],"functional":[98,136],"algorithm":[99,137],"classification":[100,138,166],"vulnerability":[102,154,185],"discovery.":[103],"compare":[105],"proposed":[107],"own":[111],"strong":[112],"baseline":[113],"as":[114,116],"well":[115],"published":[117],"results,":[118],"improvement":[121],"over":[122,194,197],"state-of-the-art":[123,161],"methods":[124],"both":[126],"evaluated":[129],"Bin2vec":[130],"49191":[132],"binaries":[133],"task,":[139],"30":[142],"CWE-IDs":[144],"including":[145],"at":[146],"least":[147],"100":[148],"CVE":[149],"entries":[150],"each":[151],"discovery":[155],"task.":[156],"set":[158],"result":[162],"reducing":[164],"error":[167],"40%":[169],"compared":[170],"source-code":[173],"inst2vec":[175],"approach,":[176],"while":[177],"working":[178],"code.":[181],"For":[182],"almost":[183],"every":[184],"class":[186],"dataset,":[189],"prediction":[191],"accuracy":[192],"is":[193],"80%":[195],"(and":[196],"90%":[198],"multiple":[200],"classes).":[201]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}