{"id":"https://openalex.org/W4415882176","doi":"https://doi.org/10.1145/3793655.3793735","title":"MalCVE: Malware Detection and CVE Association Using Large Language Models","display_name":"MalCVE: Malware Detection and CVE Association Using Large Language Models","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W4415882176","doi":"https://doi.org/10.1145/3793655.3793735"},"language":null,"primary_location":{"id":"doi:10.1145/3793655.3793735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793735","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 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793655.3793735","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120251503","display_name":"Eduard Andrei Cristea","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Eduard Andrei Cristea","raw_affiliation_strings":["Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":"https://orcid.org/0009-0005-6161-8511","affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120251504","display_name":"Petter Molnes","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Petter Molnes","raw_affiliation_strings":["Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":"https://orcid.org/0009-0006-0349-1046","affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jingyue Li","orcid":"https://orcid.org/0000-0002-7958-391X"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jingyue Li","raw_affiliation_strings":["Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":"https://orcid.org/0000-0002-7958-391X","affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204778367"],"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":"144","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9575999975204468,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9575999975204468,"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/T11644","display_name":"Spam and Phishing Detection","score":0.007699999958276749,"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/T10260","display_name":"Software Engineering Research","score":0.007000000216066837,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.8809999823570251},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6211000084877014},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5713000297546387},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5164999961853027},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/cryptovirology","display_name":"Cryptovirology","score":0.44209998846054077},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3702000081539154}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8809999823570251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307999968528748},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6211000084877014},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45239999890327454},{"id":"https://openalex.org/C84525096","wikidata":"https://www.wikidata.org/wiki/Q3506050","display_name":"Cryptovirology","level":3,"score":0.44209998846054077},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.35100001096725464},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.2685000002384186},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2535000145435333}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3793655.3793735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793735","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 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.15567","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.15567","pdf_url":"https://arxiv.org/pdf/2510.15567","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":"pmh:doi:10.48550/arxiv.2510.15567","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2510.15567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.15567","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3793655.3793735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793735","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 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Malicious":[0],"software":[1,13,25],"attacks":[2],"are":[3,29],"having":[4],"an":[5,59],"increasingly":[6],"significant":[7],"economic":[8],"impact.":[9],"Commercial":[10],"malware":[11,21,36,92,159],"detection":[12],"can":[14],"be":[15],"costly,":[16],"and":[17,37,48,75,88,113,157],"tools":[18],"that":[19,61,91,101,150,183],"attribute":[20],"to":[22,67,84,167,181],"the":[23,33,38,140,147,164],"specific":[24],"vulnerabilities":[26,39],"it":[27,40],"exploits":[28],"largely":[30],"lacking.":[31],"Understanding":[32],"connection":[34],"between":[35],"targets":[41],"is":[42,162,179],"crucial":[43],"for":[44],"analyzing":[45],"past":[46],"threats":[47],"proactively":[49],"defending":[50],"against":[51],"current":[52],"ones.":[53],"In":[54,145],"this":[55],"study,":[56],"we":[57],"propose":[58],"approach":[60],"leverages":[62],"large":[63],"language":[64],"models":[65],"(LLMs)":[66],"detect":[68],"binary":[69,103,171],"malware,":[70,172],"specifically":[71],"within":[72],"JAR":[73,126],"files,":[74],"uses":[76],"LLM":[77],"capabilities":[78],"combined":[79],"with":[80,170],"retrieval-augmented":[81],"generation":[82],"(RAG)":[83],"identify":[85],"Common":[86],"Vulnerabilities":[87],"Exposures":[89],"(CVEs)":[90],"may":[93],"exploit.":[94],"We":[95,117],"developed":[96],"a":[97,121,130,137,174],"proof-of-concept":[98],"tool,":[99],"MalCVE,":[100],"integrates":[102],"code":[104,108,152],"decompilation,":[105],"deobfuscation,":[106],"LLM-based":[107,114,151],"summarization,":[109],"semantic":[110],"similarity":[111],"search,":[112],"CVE":[115],"classification.":[116],"evaluated":[118],"MalCVE":[119,128,161],"using":[120],"benchmark":[122],"dataset":[123],"of":[124,134,139,142,176],"3,839":[125],"executables.":[127],"achieved":[129],"mean":[131],"malware-detection":[132],"accuracy":[133],"97%,":[135],"at":[136],"fraction":[138],"cost":[141],"commercial":[143],"solutions.":[144],"particular,":[146],"results":[148],"demonstrate":[149],"summarization":[153],"enables":[154],"highly":[155],"accurate":[156],"explainable":[158],"identification.":[160],"also":[163],"first":[165],"tool":[166],"associate":[168],"CVEs":[169],"achieving":[173],"recall@10":[175],"65%,":[177],"which":[178],"comparable":[180],"studies":[182],"perform":[184],"similar":[185],"analyses":[186],"on":[187],"source":[188],"code.":[189]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-21T00:00:00"}