{"id":"https://openalex.org/W4413757598","doi":"https://doi.org/10.1145/3704268.3748684","title":"Hierarchical Clustering of the SOREL Malware Corpus","display_name":"Hierarchical Clustering of the SOREL Malware Corpus","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413757598","doi":"https://doi.org/10.1145/3704268.3748684"},"language":"en","primary_location":{"id":"doi:10.1145/3704268.3748684","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3748684","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748684","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 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748684","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119451394","display_name":"S Raguvir","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122018","display_name":"University of Maryland Extension","ror":"https://ror.org/03r8q5f36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210122018"]},{"id":"https://openalex.org/I6059380","display_name":"University of Baltimore","ror":"https://ror.org/024gw2733","country_code":"US","type":"education","lineage":["https://openalex.org/I6059380"]},{"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":true,"raw_author_name":"Raguvir S","raw_affiliation_strings":["Department of Computer Science and Electrical, Engineering, UMBC, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electrical, Engineering, UMBC, Baltimore, MD, USA","institution_ids":["https://openalex.org/I4210122018","https://openalex.org/I6059380","https://openalex.org/I79272384"]}]},{"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/I4210122018","display_name":"University of Maryland Extension","ror":"https://ror.org/03r8q5f36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210122018"]},{"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"]},{"id":"https://openalex.org/I6059380","display_name":"University of Baltimore","ror":"https://ror.org/024gw2733","country_code":"US","type":"education","lineage":["https://openalex.org/I6059380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["Department of Computer Science and Electrical, Engineering, UMBC, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electrical, Engineering, UMBC, Baltimore, MD, USA","institution_ids":["https://openalex.org/I4210122018","https://openalex.org/I6059380","https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119451394"],"corresponding_institution_ids":["https://openalex.org/I4210122018","https://openalex.org/I6059380","https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33751501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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":0.9991999864578247,"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/T10734","display_name":"Information and Cyber Security","score":0.9947999715805054,"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":0.7377027273178101},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.7153884768486023},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.574468195438385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4594174027442932},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4484468102455139},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10132548213005066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7377027273178101},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.7153884768486023},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.574468195438385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4594174027442932},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4484468102455139},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10132548213005066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704268.3748684","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3748684","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748684","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 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704268.3748684","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3748684","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3748684","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 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413757598.pdf","grobid_xml":"https://content.openalex.org/works/W4413757598.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1554157714","https://openalex.org/W1947535385","https://openalex.org/W2040888993","https://openalex.org/W2125310307","https://openalex.org/W2141198770","https://openalex.org/W2150423842","https://openalex.org/W2471643592","https://openalex.org/W2734941459","https://openalex.org/W2902051546","https://openalex.org/W2998074434","https://openalex.org/W3194586437","https://openalex.org/W3208507830","https://openalex.org/W4365505506"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2097492617","https://openalex.org/W2753240997","https://openalex.org/W1764168690","https://openalex.org/W2537959205","https://openalex.org/W2740895074","https://openalex.org/W2772446090","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,41],"discuss":[1],"the":[2,21,46,52],"use":[3,22,42],"of":[4,17,23,29,38,54,62,66,78],"hierarchical":[5],"clustering":[6,30,55,84],"to":[7],"identify":[8],"similar":[9],"specimens":[10],"in":[11],"a":[12,24,76],"large":[13],"malware":[14],"corpus.":[15],"Clustering":[16],"any":[18],"kind":[19],"requires":[20,32],"distance":[25],"function,":[26],"and":[27,49,59,83],"evaluation":[28],"algorithms":[31],"criteria":[33],"that":[34],"involve":[35],"some":[36],"sort":[37],"ground":[39,47],"truth.":[40],"Jaccard":[43],"Distance":[44],"as":[45],"truth,":[48],"we":[50],"compare":[51],"results":[53],"when":[56],"using":[57],"MinHash":[58],"SuperMinHash,":[60],"both":[61],"which":[63],"are":[64],"approximations":[65],"Jaccard,":[67],"while":[68],"supposedly":[69],"being":[70],"faster.":[71],"This":[72],"work":[73],"therefore":[74],"is":[75],"study":[77],"this":[79],"tradeoff":[80],"between":[81],"speed":[82],"quality.":[85]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
