{"id":"https://openalex.org/W4297099963","doi":"https://doi.org/10.1109/dsc54232.2022.9888835","title":"Malicious and Benign URL Dataset Generation Using Character-Level LSTM Models","display_name":"Malicious and Benign URL Dataset Generation Using Character-Level LSTM Models","publication_year":2022,"publication_date":"2022-06-22","ids":{"openalex":"https://openalex.org/W4297099963","doi":"https://doi.org/10.1109/dsc54232.2022.9888835"},"language":"en","primary_location":{"id":"doi:10.1109/dsc54232.2022.9888835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsc54232.2022.9888835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Dependable and Secure Computing (DSC)","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/A5073855084","display_name":"Spencer Vecile","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Spencer Vecile","raw_affiliation_strings":["Western University,Department of Electrical and Computer Engineering,London,Canada","Department of Electrical and Computer Engineering, Western University, London, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western University,Department of Electrical and Computer Engineering,London,Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Western University, London, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020535153","display_name":"Kyle Lacroix","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kyle Lacroix","raw_affiliation_strings":["Western University,Department of Electrical and Computer Engineering,London,Canada","Department of Electrical and Computer Engineering, Western University, London, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western University,Department of Electrical and Computer Engineering,London,Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Western University, London, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012962681","display_name":"Katarina Grolinger","orcid":"https://orcid.org/0000-0003-0062-8212"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Katarina Grolinger","raw_affiliation_strings":["Western University,Department of Electrical and Computer Engineering,London,Canada","Department of Electrical and Computer Engineering, Western University, London, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western University,Department of Electrical and Computer Engineering,London,Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Western University, London, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049647213","display_name":"Jagath Samarabandu","orcid":"https://orcid.org/0009-0006-5871-6548"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jagath Samarabandu","raw_affiliation_strings":["Western University,Department of Electrical and Computer Engineering,London,Canada","Department of Electrical and Computer Engineering, Western University, London, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western University,Department of Electrical and Computer Engineering,London,Canada","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Western University, London, Canada","institution_ids":["https://openalex.org/I125749732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125749732"],"apc_list":null,"apc_paid":null,"fwci":1.9124,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89004979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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":0.9998999834060669,"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/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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8554524183273315},{"id":"https://openalex.org/keywords/blacklist","display_name":"Blacklist","score":0.7121150493621826},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5967801809310913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5358874201774597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5038015246391296},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.47196874022483826},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4327784478664398},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.378088116645813},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3750995993614197},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.26369956135749817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554524183273315},{"id":"https://openalex.org/C2781345505","wikidata":"https://www.wikidata.org/wiki/Q2535979","display_name":"Blacklist","level":2,"score":0.7121150493621826},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5967801809310913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5358874201774597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5038015246391296},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.47196874022483826},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4327784478664398},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.378088116645813},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3750995993614197},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26369956135749817},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsc54232.2022.9888835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsc54232.2022.9888835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Dependable and Secure Computing (DSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W433644524","https://openalex.org/W1499864241","https://openalex.org/W2001496424","https://openalex.org/W2090979553","https://openalex.org/W2146729596","https://openalex.org/W2250842199","https://openalex.org/W2521519773","https://openalex.org/W2765811365","https://openalex.org/W2789828921","https://openalex.org/W2921573932","https://openalex.org/W2963262350","https://openalex.org/W2995006815","https://openalex.org/W3128607711","https://openalex.org/W6629930100"],"related_works":["https://openalex.org/W3172840274","https://openalex.org/W2245533262","https://openalex.org/W50122730","https://openalex.org/W3129811130","https://openalex.org/W2265547225","https://openalex.org/W4379616178","https://openalex.org/W3185731761","https://openalex.org/W4292158217","https://openalex.org/W2181543702","https://openalex.org/W1486231179"],"abstract_inverted_index":{"As":[0],"technologies":[1],"advance,":[2],"so":[3],"do":[4,97],"the":[5,92,121,124,133,141,144,151,156,159,171,176,183,203,206,226,233,235,250,255,258],"attacks":[6],"on":[7],"them.":[8],"Cybersecurity":[9],"plays":[10],"a":[11,65,218],"significant":[12],"role":[13],"in":[14,71,264],"society":[15],"to":[16,24,45,55,84,109,115,139,154,164,249],"protect":[17],"everyone.":[18],"Malicious":[19],"URLs":[20,40,88,112,134,163,210],"are":[21],"links":[22],"designed":[23],"promote":[25],"scams,":[26],"attacks,":[27],"and":[28,74,113,137,161,194,208,222,228],"frauds.":[29],"Companies":[30],"often":[31],"have":[32],"web":[33],"filtering":[34],"algorithms":[35],"that":[36,175,202,245],"will":[37,49],"blacklist":[38],"specific":[39],"as":[41],"malicious;":[42],"however,":[43,187],"due":[44],"privacy":[46],"concerns,":[47],"they":[48,94],"not":[50],"give":[51],"outside":[52],"entities":[53],"access":[54],"their":[56],"cybersecurity":[57,72],"data.":[58],"Unfortunately,":[59],"this":[60,98,265],"lack":[61],"of":[62,123,143,205,220,260],"data":[63,70,93,126,146,178,185],"creates":[64],"dire":[66],"need":[67],"for":[68,225,257],"more":[69,262],"research":[73],"machine":[75,82],"learning":[76,83],"applications.":[77],"This":[78],"paper":[79],"proposes":[80],"using":[81],"generate":[85,110,116],"new":[86],"synthetic":[87,125,162,177,243],"characteristically":[89,247],"indistinguishable":[90],"from":[91,170],"replace.":[95],"To":[96,119],"two":[99,127],"character-level":[100,236],"long":[101],"short-term":[102],"memory":[103],"(LSTM)":[104],"models":[105],"were":[106,129,147,211],"trained,":[107],"one":[108,114],"malicious":[111,136,207,229],"benign":[117,138,209,227],"URLs.":[118],"assess":[120],"quality":[122],"tests":[128,216],"performed.":[130],"(1)":[131],"Classify":[132],"into":[135],"ensure":[140,165],"characteristics":[142,204],"original":[145],"preserved.":[148,212],"(2)":[149],"Use":[150],"Levenstein":[152,214],"ratio":[153,215],"check":[155],"similarity":[157,224],"between":[158],"real":[160,184],"sufficient":[166],"anonymization.":[167],"The":[168,213],"results":[169],"classification":[172],"test":[173],"show":[174],"classifier":[179],"only":[180],"slightly":[181],"underperformed":[182],"classifier;":[186],"with":[188],"having":[189],"accuracy,":[190],"precision,":[191],"recall,":[192],"sensitivity,":[193],"specificity":[195],"above":[196],"99%,":[197],"it":[198],"can":[199],"be":[200],"concluded":[201],"showed":[217],"mean":[219],"67%":[221],"79%":[223],"URLs,":[230],"respectively.":[231],"In":[232],"end,":[234],"LSTM":[237],"model":[238],"successfully":[239],"generated":[240],"an":[241],"anonymized,":[242],"dataset,":[244],"was":[246],"similar":[248],"original,":[251],"which":[252],"could":[253],"pave":[254],"way":[256],"publication":[259],"many":[261],"datasets":[263],"way.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}