{"id":"https://openalex.org/W7171722053","doi":"https://doi.org/10.1145/3794763.3794795","title":"Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context","display_name":"Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7171722053","doi":"https://doi.org/10.1145/3794763.3794795"},"language":null,"primary_location":{"id":"doi:10.1145/3794763.3794795","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3794763.3794795","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 34th IEEE/ACM International Conference on Program Comprehension","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3794763.3794795","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075365952","display_name":"Samuel Valenzuela","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Samuel Valenzuela","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany; Munich Center for Machine Learning, Munich, Germany and Center for Digital Technology and Management, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0001-6525-420X","affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany; Munich Center for Machine Learning, Munich, Germany and Center for Digital Technology and Management, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044468650","display_name":"Johannes Kinder","orcid":"https://orcid.org/0000-0002-8594-7839"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Kinder","raw_affiliation_strings":["Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany and Munich Center for Machine Learning, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8594-7839","affiliations":[{"raw_affiliation_string":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany and Munich Center for Machine Learning, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5942999720573425},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5733000040054321},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.5141000151634216},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4478999972343445},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4212999939918518},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3952000141143799},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.38199999928474426},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.36970001459121704},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938999891281128},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5141000151634216},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4478999972343445},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4212999939918518},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C102379954","wikidata":"https://www.wikidata.org/wiki/Q2589940","display_name":"Call graph","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C37061001","wikidata":"https://www.wikidata.org/wiki/Q3531721","display_name":"Binary Independence Model","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3794763.3794795","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3794763.3794795","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 34th IEEE/ACM International Conference on Program Comprehension","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3794763.3794795","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3794763.3794795","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 34th IEEE/ACM International Conference on Program Comprehension","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2102833942","https://openalex.org/W2132022337","https://openalex.org/W2749008552","https://openalex.org/W2888320512","https://openalex.org/W2888698761","https://openalex.org/W2892187814","https://openalex.org/W2926178846","https://openalex.org/W2945316254","https://openalex.org/W2981869278","https://openalex.org/W2997915791","https://openalex.org/W3092292656","https://openalex.org/W3093415205","https://openalex.org/W3133719257","https://openalex.org/W3172640653","https://openalex.org/W4285490409","https://openalex.org/W4285586654","https://openalex.org/W4306406265","https://openalex.org/W4308632257","https://openalex.org/W4312324806","https://openalex.org/W4313203541","https://openalex.org/W4324007217","https://openalex.org/W4383888895","https://openalex.org/W4384154511","https://openalex.org/W4385679661","https://openalex.org/W4402457354","https://openalex.org/W4411996541"],"related_works":[],"abstract_inverted_index":{"Binary":[0],"function":[1,45,58,95],"embedding":[2,76,96],"models":[3,41,86,169],"are":[4],"trained":[5],"to":[6,22,56,115],"encode":[7],"the":[8,44,64,72,88,148,153,159,167,175,193],"semantics":[9],"of":[10,25,74,84,119,122,161],"binary":[11,31,94,106],"code":[12,32,107],"in":[13,46,164,201],"such":[14,29],"a":[15,23,82],"way":[16],"that":[17,103,129,152,174,192],"they":[18],"can":[19,196],"be":[20,197],"generalized":[21],"variety":[24],"reverse":[26],"engineering":[27],"tasks,":[28,117],"as":[30,48],"search,":[33],"vulnerability":[34],"detection,":[35],"or":[36],"malware":[37],"classification.":[38],"While":[39],"many":[40],"only":[42],"take":[43],"question":[47],"contextual":[49],"input,":[50],"there":[51],"have":[52],"been":[53],"successful":[54],"attempts":[55],"improve":[57],"embeddings":[59,89],"by":[60,91],"leveraging":[61],"information":[62],"from":[63],"call":[65,154,194],"graph.":[66],"In":[67],"this":[68],"study,":[69],"we":[70,101,127,150,172],"dissect":[71],"implications":[73],"these":[75],"refinements.":[77],"We":[78],"conduct":[79],"experiments":[80],"using":[81],"range":[83],"graph-based":[85,155],"on":[87,105,139,147,188],"generated":[90],"two":[92],"state-of-the-art":[93],"models.":[97],"Integrating":[98],"inter-procedural":[99],"context,":[100],"show":[102],"improvements":[104],"similarity":[108,133],"detection":[109],"(BCSD)":[110],"will":[111],"not":[112],"necessarily":[113],"generalize":[114],"downstream":[116],"neither":[118],"semantic":[120,132],"nor":[121],"syntactic":[123,140],"nature.":[124],"More":[125],"generally,":[126],"find":[128,151],"optimizing":[130],"for":[131,181,185],"tasks":[134],"correlates":[135],"with":[136],"worse":[137],"performance":[138],"tasks.":[141],"By":[142],"conducting":[143],"an":[144],"explanatory":[145],"analysis":[146],"dataset,":[149],"enhancements":[156],"significantly":[157],"enhance":[158],"robustness":[160],"embeddings,":[162],"particularly":[163],"scenarios":[165],"where":[166],"initial":[168],"struggle.":[170],"Furthermore,":[171],"observe":[173],"added":[176],"context":[177],"is":[178],"more":[179],"beneficial":[180],"namespace-related":[182],"functions":[183],"than":[184],"those":[186],"focused":[187],"individual":[189],"logic,":[190],"confirming":[191],"graph":[195],"leveraged":[198],"most":[199],"effectively":[200],"context-dependent":[202],"scenarios.":[203]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-30T00:00:00"}