{"id":"https://openalex.org/W1966800919","doi":"https://doi.org/10.1109/malware.2012.6461014","title":"A scalable search index for binary files","display_name":"A scalable search index for binary files","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W1966800919","doi":"https://doi.org/10.1109/malware.2012.6461014","mag":"1966800919"},"language":"en","primary_location":{"id":"doi:10.1109/malware.2012.6461014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/malware.2012.6461014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 7th International Conference on Malicious and Unwanted Software","raw_type":"proceedings-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/A5085584133","display_name":"Wesley Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I2802039673","display_name":"California Miramar University","ror":"https://ror.org/04phxq043","country_code":"US","type":"education","lineage":["https://openalex.org/I2802039673"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley Jin","raw_affiliation_strings":["CMU, USA","CMU-USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMU, USA","institution_ids":["https://openalex.org/I2802039673"]},{"raw_affiliation_string":"CMU-USA","institution_ids":["https://openalex.org/I2802039673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055466731","display_name":"Charles Hines","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles Hines","raw_affiliation_strings":["CERT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERT, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030293121","display_name":"Cory Cohen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cory Cohen","raw_affiliation_strings":["CERT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERT, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071484632","display_name":"Priya Narasimhan","orcid":"https://orcid.org/0000-0001-9100-0943"},"institutions":[{"id":"https://openalex.org/I2802039673","display_name":"California Miramar University","ror":"https://ror.org/04phxq043","country_code":"US","type":"education","lineage":["https://openalex.org/I2802039673"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priya Narasimhan","raw_affiliation_strings":["CMU, USA","CMU-USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMU, USA","institution_ids":["https://openalex.org/I2802039673"]},{"raw_affiliation_string":"CMU-USA","institution_ids":["https://openalex.org/I2802039673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4423,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70867295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1741","issue":null,"first_page":"94","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9983000159263611,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8780468702316284},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.8210071325302124},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7019148468971252},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6646514534950256},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6248396039009094},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5722412467002869},{"id":"https://openalex.org/keywords/binary-search-algorithm","display_name":"Binary search algorithm","score":0.5354502201080322},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5325015783309937},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.5085877180099487},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49487704038619995},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.45524993538856506},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.44765907526016235},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4419931173324585},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3728461265563965},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.21850648522377014},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1523485779762268},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15082088112831116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1125372052192688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0843115746974945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8780468702316284},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.8210071325302124},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7019148468971252},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6646514534950256},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6248396039009094},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5722412467002869},{"id":"https://openalex.org/C121610932","wikidata":"https://www.wikidata.org/wiki/Q243754","display_name":"Binary search algorithm","level":3,"score":0.5354502201080322},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5325015783309937},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.5085877180099487},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49487704038619995},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.45524993538856506},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.44765907526016235},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4419931173324585},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3728461265563965},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.21850648522377014},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1523485779762268},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15082088112831116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1125372052192688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0843115746974945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/malware.2012.6461014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/malware.2012.6461014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 7th International Conference on Malicious and Unwanted Software","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W125979907","https://openalex.org/W1524501441","https://openalex.org/W1532325895","https://openalex.org/W1786504122","https://openalex.org/W2033943297","https://openalex.org/W2068066080","https://openalex.org/W2076471773","https://openalex.org/W2140453381","https://openalex.org/W2152437528","https://openalex.org/W2752061190","https://openalex.org/W2752853835","https://openalex.org/W4213009331","https://openalex.org/W6605088862"],"related_works":["https://openalex.org/W2086572746","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W1662107788","https://openalex.org/W121740227","https://openalex.org/W2491058909","https://openalex.org/W2407380583","https://openalex.org/W2030942072","https://openalex.org/W1989507269","https://openalex.org/W2050771811"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,38,54,62,83,112,134],"locate":[3],"specific":[4],"byte-sequences":[5],"in":[6,14,106],"large":[7],"collections":[8,98],"of":[9,41,52,99,126],"binary":[10,100],"files":[11,75],"is":[12],"important":[13],"many":[15,57],"applications,":[16],"especially":[17],"malware":[18],"analysis.":[19],"However,":[20],"it":[21],"can":[22,49],"be":[23],"a":[24,90,138],"time":[25,132],"consuming":[26],"process.":[27],"Researchers":[28],"and":[29,46,65,95,136],"analysts,":[30],"such":[31],"as":[32],"those":[33],"at":[34],"CERT,":[35],"often":[36],"have":[37],"search":[39,58,86],"terabytes":[40],"data":[42,127],"for":[43,73,93],"characteristic":[44],"patterns":[45],"signatures,":[47],"which":[48],"take":[50],"upwards":[51],"days":[53,111],"complete.":[55],"Although":[56],"systems,":[59],"designed":[60],"specifically":[61],"expedite":[63],"text":[64],"metadata":[66],"queries,":[67],"exist,":[68],"these":[69],"tools":[70],"are":[71],"unsuitable":[72],"searching":[74,94],"containing":[76],"arbitrary":[77],"bytes.":[78],"By":[79],"using":[80,114],"probabilistic":[81],"techniques":[82],"pre-filter":[84],"likely":[85],"candidates,":[87],"we":[88],"present":[89],"scalable":[91],"architecture":[92],"indexing":[96],"terabyte-size":[97],"files.":[101],"Our":[102],"implementation":[103],"performs":[104],"searches":[105],"minutes":[107],"that":[108],"would":[109],"required":[110,133],"complete":[113],"iterative":[115],"techniques.":[116],"It":[117],"also":[118],"reduces":[119],"storage":[120],"costs":[121],"by":[122],"balancing":[123],"the":[124,130],"amount":[125],"indexed":[128],"with":[129],"total":[131],"conduct":[135],"verify":[137],"query.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
