{"id":"https://openalex.org/W2894779647","doi":"https://doi.org/10.1145/3209280.3229085","title":"Hash-Grams","display_name":"Hash-Grams","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2894779647","doi":"https://doi.org/10.1145/3209280.3229085","mag":"2894779647"},"language":"en","primary_location":{"id":"doi:10.1145/3209280.3229085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11603/11343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Laboratory for Physical Sciences, Booz Allen Hamilton"],"affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences, Booz Allen Hamilton","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025012064","display_name":"Charles Nicholas","orcid":"https://orcid.org/0000-0001-9494-7139"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["Univ. of Maryland, Baltimore County"],"affiliations":[{"raw_affiliation_string":"Univ. of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068036546"],"corresponding_institution_ids":["https://openalex.org/I1322124587"],"apc_list":null,"apc_paid":null,"fwci":1.6514,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85341113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9969000220298767,"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/hash-function","display_name":"Hash function","score":0.8061926364898682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916388511657715},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7634729146957397},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6409929990768433},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5739783048629761},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4218837022781372},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36636656522750854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36276066303253174}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.8061926364898682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916388511657715},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7634729146957397},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6409929990768433},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5739783048629761},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4218837022781372},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36636656522750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36276066303253174},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3209280.3229085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209280.3229085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:mdsoar.org:11603/11343","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/11343","pdf_url":null,"source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.13016/m2q814w51","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2q814w51","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mdsoar.org:11603/11343","is_oa":true,"landing_page_url":"http://hdl.handle.net/11603/11343","pdf_url":null,"source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W151938044","https://openalex.org/W1553409264","https://openalex.org/W2015645889","https://openalex.org/W2017062116","https://openalex.org/W2018989507","https://openalex.org/W2070996757","https://openalex.org/W2078396547","https://openalex.org/W2079656678","https://openalex.org/W2121749752","https://openalex.org/W2122825543","https://openalex.org/W2143996849","https://openalex.org/W2144112223","https://openalex.org/W2518866423","https://openalex.org/W2608296545","https://openalex.org/W2766343248","https://openalex.org/W2766353929","https://openalex.org/W2792663539","https://openalex.org/W2963437896","https://openalex.org/W2963993553","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"N-grams":[0],"have":[1],"long":[2],"been":[3],"used":[4],"as":[5,21],"features":[6],"for":[7,59],"classification":[8,60,98],"problems,":[9],"and":[10,44],"their":[11],"distribution":[12],"often":[13],"allows":[14],"selection":[15,31,80],"of":[16,74,86],"the":[17,65],"top-k":[18,30,56,79],"occurring":[19],"n-grams":[20],"a":[22,34,83],"reliable":[23],"first-pass":[24],"to":[25,54,71],"feature":[26,57],"selection.":[27],"However,":[28],"this":[29,47],"can":[32,68],"be":[33,69],"performance":[35],"bottleneck,":[36],"especially":[37],"when":[38],"dealing":[39],"with":[40],"massive":[41],"item":[42],"sets":[43],"corpora.":[45],"In":[46],"work":[48],"we":[49,92],"introduce":[50],"Hash-Grams,":[51],"an":[52],"approach":[53,67],"perform":[55],"mining":[58],"problems.":[61],"We":[62],"show":[63,93],"that":[64],"Hash-Gram":[66],"up":[70],"three":[72],"orders":[73],"magnitude":[75],"faster":[76],"than":[77],"exact":[78],"algorithms.":[81],"Using":[82],"malware":[84],"corpus":[85],"over":[87],"2":[88],"TB":[89],"in":[90],"size,":[91],"how":[94],"Hash-Grams":[95],"retain":[96],"comparable":[97],"accuracy,":[99],"while":[100],"dramatically":[101],"reducing":[102],"computational":[103],"requirements.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-10-12T00:00:00"}