{"id":"https://openalex.org/W4307510779","doi":"https://doi.org/10.1145/3569933","title":"<tt>sem2vec</tt> : Semantics-aware Assembly Tracelet Embedding","display_name":"<tt>sem2vec</tt> : Semantics-aware Assembly Tracelet Embedding","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4307510779","doi":"https://doi.org/10.1145/3569933"},"language":"en","primary_location":{"id":"doi:10.1145/3569933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3569933","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/A5027062760","display_name":"Huaijin Wang","orcid":"https://orcid.org/0000-0002-1066-0331"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Huaijin Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-1066-0331","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101728918","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0001-7680-2817"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-7680-2817","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328264","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0866-0308"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-0866-0308","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007842132","display_name":"Qiyi Tang","orcid":"https://orcid.org/0000-0002-8200-7518"},"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":"Qiyi Tang","raw_affiliation_strings":["Keen Security Lab, Tencent, China"],"raw_orcid":"https://orcid.org/0000-0002-8200-7518","affiliations":[{"raw_affiliation_string":"Keen Security Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069450513","display_name":"Sen Nie","orcid":"https://orcid.org/0000-0003-4154-2941"},"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":"Sen Nie","raw_affiliation_strings":["Keen Security Lab, Tencent, China"],"raw_orcid":"https://orcid.org/0000-0003-4154-2941","affiliations":[{"raw_affiliation_string":"Keen Security Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409340","display_name":"Shi Wu","orcid":"https://orcid.org/0000-0002-6842-7487"},"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":"Shi Wu","raw_affiliation_strings":["Keen Security Lab, Tencent, China"],"raw_orcid":"https://orcid.org/0000-0002-6842-7487","affiliations":[{"raw_affiliation_string":"Keen Security Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.1948,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9658079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":"4","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9934999942779541,"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":0.8946120142936707},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6238923668861389},{"id":"https://openalex.org/keywords/symbolic-execution","display_name":"Symbolic execution","score":0.5588010549545288},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5529900193214417},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5252342224121094},{"id":"https://openalex.org/keywords/control-flow-graph","display_name":"Control flow graph","score":0.5248406529426575},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.49934816360473633},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.44503793120384216},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.4252026677131653},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.38413530588150024},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3184497654438019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2744273245334625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8946120142936707},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6238923668861389},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.5588010549545288},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5529900193214417},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5252342224121094},{"id":"https://openalex.org/C27458966","wikidata":"https://www.wikidata.org/wiki/Q1187693","display_name":"Control flow graph","level":2,"score":0.5248406529426575},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.49934816360473633},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.44503793120384216},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4252026677131653},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38413530588150024},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3184497654438019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2744273245334625},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3569933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3569933","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-128553","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-128553","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W157706324","https://openalex.org/W1480909796","https://openalex.org/W1525120920","https://openalex.org/W1604459715","https://openalex.org/W1690253345","https://openalex.org/W1863385414","https://openalex.org/W1989310296","https://openalex.org/W2009614414","https://openalex.org/W2010841095","https://openalex.org/W2038159719","https://openalex.org/W2041839827","https://openalex.org/W2064675550","https://openalex.org/W2066220442","https://openalex.org/W2067982285","https://openalex.org/W2068211976","https://openalex.org/W2069870183","https://openalex.org/W2071353749","https://openalex.org/W2081105932","https://openalex.org/W2081561469","https://openalex.org/W2112725702","https://openalex.org/W2117583561","https://openalex.org/W2125260159","https://openalex.org/W2138788987","https://openalex.org/W2153579005","https://openalex.org/W2165597437","https://openalex.org/W2414803796","https://openalex.org/W2514974017","https://openalex.org/W2547625248","https://openalex.org/W2560252021","https://openalex.org/W2577142429","https://openalex.org/W2579698096","https://openalex.org/W2604983939","https://openalex.org/W2612690371","https://openalex.org/W2618615322","https://openalex.org/W2627063456","https://openalex.org/W2670925489","https://openalex.org/W2749008552","https://openalex.org/W2768013588","https://openalex.org/W2790911601","https://openalex.org/W2795052548","https://openalex.org/W2886694146","https://openalex.org/W2887364112","https://openalex.org/W2901689459","https://openalex.org/W2926178846","https://openalex.org/W2963408280","https://openalex.org/W2963598554","https://openalex.org/W2963723316","https://openalex.org/W2964150020","https://openalex.org/W2964872665","https://openalex.org/W2965857891","https://openalex.org/W2970066309","https://openalex.org/W2970641574","https://openalex.org/W2979826702","https://openalex.org/W2989703616","https://openalex.org/W3007413911","https://openalex.org/W3011013751","https://openalex.org/W3033775865","https://openalex.org/W3034303554","https://openalex.org/W3098380913","https://openalex.org/W3101767350","https://openalex.org/W3104712907","https://openalex.org/W3105867435","https://openalex.org/W3105926539","https://openalex.org/W3166956180","https://openalex.org/W4247464060","https://openalex.org/W4294170691","https://openalex.org/W6606400708","https://openalex.org/W6636411187","https://openalex.org/W6767098714"],"related_works":["https://openalex.org/W650988184","https://openalex.org/W2162410319","https://openalex.org/W2137356287","https://openalex.org/W4321184925","https://openalex.org/W2138385884","https://openalex.org/W1483618713","https://openalex.org/W2166895275","https://openalex.org/W2091491463","https://openalex.org/W2274607126","https://openalex.org/W116894366"],"abstract_inverted_index":{"Binary":[0],"code":[1,84],"similarity":[2,33],"is":[3,55,177],"the":[4,36,93,119,162],"foundation":[5],"of":[6,29,51,99,147],"many":[7],"security":[8],"and":[9,76,111,131,176,184,203],"software":[10],"engineering":[11],"applications.":[12],"Recent":[13],"works":[14],"leverage":[15],"deep":[16],"neural":[17,155],"networks":[18],"(DNN)":[19],"to":[20,58,69,127,144,157],"learn":[21],"a":[22,82,166,194,205],"numeric":[23,37],"vector":[24],"representation":[25],"(namely,":[26],"embeddings":[27,146,160,199],")":[28],"assembly":[30,52,101],"functions,":[31],"enabling":[32],"analysis":[34],"in":[35,208],"space.":[38],"However,":[39],"existing":[40],"DNN-based":[41],"techniques":[42],"capture":[43],"syntactic-,":[44],"control":[45],"flow-,":[46],"or":[47],"data":[48],"flow-level":[49],"information":[50,134],"code,":[53],"which":[54],"too":[56],"coarse-grained":[57],"represent":[59],"program":[60],"functionality.":[61],"These":[62],"methods":[63,187],"can":[64],"suffer":[65],"from":[66,89,118],"low":[67],"robustness":[68],"challenging":[70],"settings":[71],"such":[72],"as":[73],"compiler":[74],"optimizations":[75],"obfuscations.":[77],"We":[78,123,138,191],"present":[79],"sem2vec":[80,172,202],",":[81,108],"binary":[83],"embedding":[85,164,175],"framework":[86],"that":[87,115,171],"learns":[88],"semantics":[90],".":[91],"Given":[92],"control-flow":[94],"graph":[95,154],"(CFG),":[96],"34":[97],"pages.":[98],"an":[100],"function,":[102],"we":[103,152],"divide":[104],"it":[105],"into":[106,161],"tracelets":[107],"denoting":[109],"continuous":[110],"short":[112],"execution":[113,126,149],"traces":[114],"are":[116],"reachable":[117],"function":[120],"entry":[121],"point.":[122],"use":[124,153],"symbolic":[125,129,148],"extract":[128],"constraints":[130],"other":[132],"auxiliary":[133],"on":[135],"each":[136],"tracelet.":[137],"then":[139],"train":[140],"masked":[141],"language":[142],"models":[143],"compute":[145],"outputs.":[150],"Last,":[151],"networks,":[156],"aggregate":[158],"tracelet":[159],"CFG-level":[163],"for":[165],"function.":[167],"Our":[168],"evaluation":[169],"shows":[170],"extracts":[173],"high-quality":[174],"robust":[178],"against":[179],"different":[180],"compilers,":[181],"optimizations,":[182],"architectures,":[183],"popular":[185],"obfuscation":[186],"including":[188],"virtualization":[189],"obfuscation.":[190],"further":[192],"augment":[193],"vulnerability":[195,209],"search":[196,210],"application":[197],"with":[198],"computed":[200],"by":[201],"demonstrate":[204],"significant":[206],"improvement":[207],"accuracy.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2022-11-02T00:00:00"}
