{"id":"https://openalex.org/W2980552833","doi":"https://doi.org/10.1145/3358695.3361751","title":"SeedsMiner: Accurate URL Blacklist-Generation Based on Efficient OSINT Seed Collection","display_name":"SeedsMiner: Accurate URL Blacklist-Generation Based on Efficient OSINT Seed Collection","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980552833","doi":"https://doi.org/10.1145/3358695.3361751","mag":"2980552833"},"language":"en","primary_location":{"id":"doi:10.1145/3358695.3361751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358695.3361751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence - Companion Volume","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064728894","display_name":"Yasuyuki Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuyuki Tanaka","raw_affiliation_strings":["NTT Communications Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communications Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000062274","display_name":"Kashima Shingo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shingo Kashima","raw_affiliation_strings":["NTT Communications Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communications Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9994999766349792,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/blacklist","display_name":"Blacklist","score":0.9888609647750854},{"id":"https://openalex.org/keywords/blacklisting","display_name":"Blacklisting","score":0.9737484455108643},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.9007320404052734},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.751621425151825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324268221855164},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.7269769906997681},{"id":"https://openalex.org/keywords/botnet","display_name":"Botnet","score":0.5652016997337341},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.5501051545143127},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.5430765151977539},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3994208574295044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1263352334499359}],"concepts":[{"id":"https://openalex.org/C2781345505","wikidata":"https://www.wikidata.org/wiki/Q2535979","display_name":"Blacklist","level":2,"score":0.9888609647750854},{"id":"https://openalex.org/C2779797433","wikidata":"https://www.wikidata.org/wiki/Q632959","display_name":"Blacklisting","level":2,"score":0.9737484455108643},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.9007320404052734},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.751621425151825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324268221855164},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.7269769906997681},{"id":"https://openalex.org/C22735295","wikidata":"https://www.wikidata.org/wiki/Q317671","display_name":"Botnet","level":3,"score":0.5652016997337341},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.5501051545143127},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.5430765151977539},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3994208574295044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1263352334499359},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3358695.3361751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358695.3361751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence - Companion Volume","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1501523446","https://openalex.org/W1963674123","https://openalex.org/W2102475112","https://openalex.org/W2139868346","https://openalex.org/W2146729596","https://openalex.org/W2966513656","https://openalex.org/W6606609320","https://openalex.org/W7075325720"],"related_works":["https://openalex.org/W2894268960","https://openalex.org/W2901413379","https://openalex.org/W2314036247","https://openalex.org/W3087358037","https://openalex.org/W2591411003","https://openalex.org/W1780512231","https://openalex.org/W2920294491","https://openalex.org/W2460146231","https://openalex.org/W3165106224","https://openalex.org/W2290880970","https://openalex.org/W2743459917","https://openalex.org/W2946356375","https://openalex.org/W2065823359","https://openalex.org/W1506884343","https://openalex.org/W2519419790","https://openalex.org/W2766836609","https://openalex.org/W1586406983","https://openalex.org/W3118802385","https://openalex.org/W2056920038","https://openalex.org/W2786167699"],"abstract_inverted_index":{"Nowadays,":[0],"increasing":[1],"Internet":[2,31,54],"use":[3,84],"is":[4,44,62,75,112],"plagued":[5],"by":[6,146,162],"malicious":[7,20,37,94,136],"activity.":[8],"Drive-by":[9],"downloads":[10],"are":[11,22,32],"still":[12],"a":[13,48,89],"serious":[14],"problem.":[15],"Furthermore,":[16],"new":[17],"kinds":[18],"of":[19,30,70,91,142,172],"sites":[21],"increasing.":[23],"Published":[24],"analysis":[25],"has":[26],"reported":[27],"that":[28,130,159],"10%":[29],"malicious.":[33],"To":[34],"countermeasure":[35],"these":[36],"URLs,":[38,137],"blacklisting":[39],"based":[40,106],"on":[41,58,107],"threat":[42],"intelligence":[43],"widely":[45],"used":[46],"as":[47],"multilayer":[49],"defense":[50],"mechanism":[51],"in":[52,167],"modern":[53],"security":[55],"techniques.":[56],"Blacklisting":[57],"the":[59,80,143,173],"network":[60],"side":[61],"especially":[63],"effective":[64],"for":[65],"protecting":[66],"critical":[67],"information":[68,100,111,119],"infrastructure":[69],"various":[71],"industries":[72],"because":[73],"it":[74],"not":[76],"necessary":[77],"to":[78,83,124,152],"change":[79],"configuration":[81],"or":[82,133],"system":[85],"resources.":[86],"We":[87,156],"propose":[88],"method":[90,149,164],"collecting":[92],"efficiently":[93],"candidate":[95],"URLs":[96],"(seed)":[97],"from":[98],"open":[99,110],"and":[101,138,170],"generating":[102],"highly":[103],"accurate":[104],"blacklists":[105],"information.":[108],"This":[109],"called":[113],"\u201cOpen":[114],"Source":[115],"Intelligence\u201d":[116],"(OSINT).":[117],"OSINT":[118],"must":[120],"be":[121],"examined":[122],"carefully":[123],"detect":[125],"inaccuracies.":[126],"Our":[127],"seed":[128],"collector":[129],"collects":[131],"50%":[132],"more":[134],"truly":[135],"we":[139],"showed":[140,158],"75%":[141],"blacklist":[144],"generated":[145],"our":[147,163],"proposed":[148],"was":[150,165,175],"unknown":[151],"Google":[153],"Safe":[154],"Browsing.":[155],"also":[157],"malware":[160,174],"collected":[161],"rich":[166],"family":[168],"variations,":[169],"23%":[171],"unknown.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
