{"id":"https://openalex.org/W4387874118","doi":"https://doi.org/10.1145/3618257.3624845","title":"An LLM-based Framework for Fingerprinting Internet-connected Devices","display_name":"An LLM-based Framework for Fingerprinting Internet-connected Devices","publication_year":2023,"publication_date":"2023-10-23","ids":{"openalex":"https://openalex.org/W4387874118","doi":"https://doi.org/10.1145/3618257.3624845"},"language":"en","primary_location":{"id":"doi:10.1145/3618257.3624845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3618257.3624845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3618257.3624845","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM on Internet Measurement Conference","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/10.1145/3618257.3624845","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068512201","display_name":"Armin Sarabi","orcid":"https://orcid.org/0000-0002-1431-7434"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Armin Sarabi","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-1431-7434","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010724961","display_name":"Tongxin Yin","orcid":"https://orcid.org/0000-0002-6166-3890"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tongxin Yin","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-6166-3890","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101967011","display_name":"Mingyan Liu","orcid":"https://orcid.org/0000-0003-3295-9200"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyan Liu","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0003-3295-9200","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068512201"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":4.2602,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95401247,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"478","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9977999925613403,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9977999925613403,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.996399998664856,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8239918947219849},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6416072249412537},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5989437103271484},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5111890435218811},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.47496625781059265},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4434260129928589},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4318960905075073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42611658573150635},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4140131175518036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3677302598953247},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3474422097206116},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24835097789764404},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10714724659919739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239918947219849},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6416072249412537},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5989437103271484},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5111890435218811},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.47496625781059265},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4434260129928589},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4318960905075073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42611658573150635},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4140131175518036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3677302598953247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3474422097206116},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24835097789764404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10714724659919739},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3618257.3624845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3618257.3624845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3618257.3624845","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM on Internet Measurement Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3618257.3624845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3618257.3624845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3618257.3624845","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM on Internet Measurement Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3963731845","display_name":null,"funder_award_id":"2012001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4820137873","display_name":null,"funder_award_id":"CNS-2012001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5081320305","display_name":null,"funder_award_id":"CNS2012001","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387874118.pdf","grobid_xml":"https://content.openalex.org/works/W4387874118.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2001637908","https://openalex.org/W2112736324","https://openalex.org/W2612690371","https://openalex.org/W2621148797","https://openalex.org/W2794584163","https://openalex.org/W2799441662","https://openalex.org/W2800412265","https://openalex.org/W2886072232","https://openalex.org/W2895807258","https://openalex.org/W2902827568","https://openalex.org/W2950767885","https://openalex.org/W2953381066","https://openalex.org/W2961816263","https://openalex.org/W3044145154","https://openalex.org/W3101877327","https://openalex.org/W4292779060","https://openalex.org/W4299301436","https://openalex.org/W4323362675","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501","https://openalex.org/W2964413124"],"abstract_inverted_index":{"In":[0],"this":[1,24,52],"paper":[2],"we":[3,146],"propose":[4],"the":[5,89,115,123,183],"use":[6],"of":[7,41,43,91,99,125,139,186],"large":[8,184],"language":[9,32,175],"models":[10,176],"(LLMs)":[11],"for":[12,75,122,169],"characterizing,":[13],"clustering,":[14],"and":[15,94,113,143,152,181],"fingerprinting":[16],"raw":[17,127],"text":[18],"obtained":[19,45,116],"from":[20,46],"network":[21],"measurements.":[22],"To":[23],"end,":[25],"We":[26,49,103,130],"first":[27],"train":[28],"a":[29,37,55,92,109],"transformer-based":[30],"masked":[31],"model,":[33],"namely":[34],"RoBERTa,":[35],"on":[36],"dataset":[38],"containing":[39],"hundreds":[40],"millions":[42],"banners":[44,107],"Internet-wide":[47],"scans.":[48,191],"further":[50,104],"fine-tune":[51],"model":[53],"using":[54,108],"contrastive":[56],"loss":[57],"function":[58],"(driven":[59],"by":[60,160,172,189],"domain":[61],"knowledge)":[62],"to":[63,84,118,134,177],"produce":[64],"temporally":[65],"stable":[66],"numerical":[67],"representations":[68],"(embeddings)":[69],"that":[70,145,155],"can":[71,147],"be":[72],"used":[73],"out-of-the-box":[74],"downstream":[76],"learning":[77],"tasks.":[78],"Our":[79,162],"embeddings":[80,98],"are":[81],"robust,":[82],"resilient":[83],"small":[85],"random":[86],"changes":[87],"in":[88],"content":[90],"banner,":[93],"maintain":[95],"proximity":[96],"between":[97],"similar":[100],"hardware/software":[101],"products.":[102],"cluster":[105],"HTTP":[106],"density-based":[110],"approach":[111],"(HDBSCAN),":[112],"examine":[114],"clusters":[117],"generate":[119],"text-based":[120],"fingerprints":[121,133],"purpose":[124],"labeling":[126],"scan":[128],"data.":[129],"compare":[131],"our":[132],"Recog,":[135],"an":[136,166],"existing":[137],"database":[138],"manually":[140],"curated":[141],"fingerprints,":[142],"show":[144],"identify":[148],"new":[149],"IoT":[150],"devices":[151],"server":[153],"products":[154],"were":[156],"not":[157],"previously":[158],"captured":[159],"Recog.":[161],"proposed":[163],"methodology":[164],"poses":[165],"important":[167],"direction":[168],"future":[170],"research":[171],"utilizing":[173],"state-of-the-art":[174],"automatically":[178],"analyze,":[179],"interpret,":[180],"label":[182],"amounts":[185],"data":[187],"generated":[188],"Internet":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}