{"id":"https://openalex.org/W4387355993","doi":"https://doi.org/10.48550/arxiv.2310.01835","title":"EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis","display_name":"EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis","publication_year":2023,"publication_date":"2023-10-03","ids":{"openalex":"https://openalex.org/W4387355993","doi":"https://doi.org/10.48550/arxiv.2310.01835"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.01835","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01835","pdf_url":"https://arxiv.org/pdf/2310.01835","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.01835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091668577","display_name":"Dragos Corlatescu","orcid":"https://orcid.org/0000-0002-7994-9950","observed_orcids":["https://orcid.org/0000-0002-7994-9950"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corlatescu, Dragos Georgian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020916426","display_name":"Alexandru Dinu","orcid":"https://orcid.org/0000-0001-6285-1458","observed_orcids":["https://orcid.org/0000-0001-6285-1458"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinu, Alexandru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072054173","display_name":"Mihaela G\u0103man","orcid":"https://orcid.org/0000-0001-7751-6759","observed_orcids":["https://orcid.org/0000-0001-7751-6759"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaman, Mihaela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018046137","display_name":"Paul Sumedrea","orcid":"https://orcid.org/0009-0002-3251-0534","observed_orcids":["https://orcid.org/0009-0002-3251-0534"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumedrea, Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.0,"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/T11424","display_name":"Security and Verification in Computing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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-classification","display_name":"malware classification","score":0.6359999775886536},{"id":"https://openalex.org/keywords/ember-dataset","display_name":"EMBER dataset","score":0.7229999899864197},{"id":"https://openalex.org/keywords/binary-files","display_name":"binary files","score":0.6019999980926514},{"id":"https://openalex.org/keywords/virustotal","display_name":"VirusTotal","score":0.9210000038146973},{"id":"https://openalex.org/keywords/similarity-search","display_name":"similarity search","score":0.46299999952316284}],"concepts":[{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.8213323354721069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244238257408142},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6724259853363037},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5689342021942139},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5455827116966248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4880591630935669},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47891104221343994},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4770209789276123},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4721560478210449},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46100303530693054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40320584177970886},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33727025985717773},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09687882661819458},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07283025979995728},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.01835","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01835","pdf_url":"https://arxiv.org/pdf/2310.01835","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.01835","doi":"https://doi.org/10.48550/arxiv.2310.01835","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.01835","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.01835","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01835","pdf_url":"https://arxiv.org/pdf/2310.01835","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387355993.pdf","grobid_xml":"https://content.openalex.org/works/W4387355993.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2798159728"],"related_works":["https://openalex.org/W4412876938","https://openalex.org/W7130482152","https://openalex.org/W3115413663","https://openalex.org/W2997359200","https://openalex.org/W4411918148","https://openalex.org/W1966695331","https://openalex.org/W2519371923","https://openalex.org/W4408111120","https://openalex.org/W2945404328","https://openalex.org/W7125460885"],"abstract_inverted_index":{"In":[0],"recent":[1],"years":[2],"there":[3],"has":[4],"been":[5],"a":[6,52],"shift":[7],"from":[8,112],"heuristics-based":[9],"malware":[10,119,132,167],"detection":[11,94],"towards":[12],"machine":[13,31],"learning,":[14],"which":[15],"proves":[16],"to":[17,33,37,98,135],"be":[18,34],"more":[19],"robust":[20],"in":[21,41,68,77,90,102,139],"the":[22,42,56,66,69,81,91,100,103,117,140,171,184],"current":[23],"heavily":[24],"adversarial":[25],"threat":[26],"landscape.":[27],"While":[28],"we":[29,49,63,148,161,180],"acknowledge":[30],"learning":[32],"better":[35],"equipped":[36],"mine":[38],"for":[39,59,186],"patterns":[40],"increasingly":[43],"high":[44],"amounts":[45],"of":[46,55,93,105,116,154],"similar-looking":[47],"files,":[48,110],"also":[50],"note":[51],"remarkable":[53],"scarcity":[54],"data":[57,121,177],"available":[58],"similarity-targeted":[60],"research.":[61],"Moreover,":[62],"observe":[64],"that":[65,156],"focus":[67],"few":[70],"related":[71],"works":[72],"falls":[73],"on":[74,108,175],"quantifying":[75],"similarity":[76,106,127,141,193],"malware,":[78],"often":[79],"overlooking":[80],"clean":[82],"data.":[83],"This":[84],"one-sided":[85],"quantification":[86],"is":[87,145],"especially":[88],"dangerous":[89],"context":[92],"bypass.":[95],"We":[96,123],"propose":[97],"address":[99],"deficiencies":[101],"space":[104],"research":[107,138],"binary":[109],"starting":[111],"EMBER":[113,125],"-":[114],"one":[115],"largest":[118],"classification":[120],"sets.":[122],"enhance":[124],"with":[126,164],"information":[128],"as":[129,131],"well":[130],"class":[133,168,188],"tags,":[134],"enable":[136],"further":[137],"space.":[142],"Our":[143],"contribution":[144],"threefold:":[146],"(1)":[147],"publish":[149],"EMBERSim,":[150],"an":[151],"augmented":[152],"version":[153],"EMBER,":[155],"includes":[157],"similarity-informed":[158],"tags;":[159],"(2)":[160],"enrich":[162],"EMBERSim":[163],"automatically":[165],"determined":[166],"tags":[169],"using":[170],"open-source":[172],"tool":[173],"AVClass":[174],"VirusTotal":[176],"and":[178,182,191],"(3)":[179],"describe":[181],"share":[183],"implementation":[185],"our":[187],"scoring":[189],"technique":[190],"leaf":[192],"method.":[194]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-10-05T00:00:00"}