{"id":"https://openalex.org/W4410636403","doi":"https://doi.org/10.1145/3701716.3715469","title":"Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Models","display_name":"Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Models","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636403","doi":"https://doi.org/10.1145/3701716.3715469"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715469","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715469","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715469","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hoang Cuong Nguyen","orcid":"https://orcid.org/0009-0007-4421-2995"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hoang Cuong Nguyen","raw_affiliation_strings":["Swinburne University of Technology, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003311970","display_name":"Shahroz Tariq","orcid":"https://orcid.org/0000-0001-9090-0579"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shahroz Tariq","raw_affiliation_strings":["CSIRO's Data61, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO's Data61, Sydney, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000678710","display_name":"Mohan Baruwal Chhetri","orcid":"https://orcid.org/0000-0002-6138-7742"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohan Baruwal Chhetri","raw_affiliation_strings":["CSIRO's Data61, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO's Data61, Melbourne, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055692975","display_name":"Quoc Bao Vo","orcid":"https://orcid.org/0000-0002-7404-110X"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bao Quoc Vo","raw_affiliation_strings":["Swinburne University of Technology, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57093077"],"apc_list":null,"apc_paid":null,"fwci":51.256,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99875002,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"942","last_page":"946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12572","display_name":"Intelligence, Security, War Strategy","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9470000267028809,"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":0.7605395317077637},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7134349346160889},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5408288836479187},{"id":"https://openalex.org/keywords/intelligence-analysis","display_name":"Intelligence analysis","score":0.43099451065063477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605395317077637},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7134349346160889},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5408288836479187},{"id":"https://openalex.org/C517642484","wikidata":"https://www.wikidata.org/wiki/Q2388514","display_name":"Intelligence analysis","level":2,"score":0.43099451065063477},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3701716.3715469","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715469","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715469","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.03147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.03147","pdf_url":"https://arxiv.org/pdf/2505.03147","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715469","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715469","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715469","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320386","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636403.pdf","grobid_xml":"https://content.openalex.org/works/W4410636403.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3199212845","https://openalex.org/W3211888892","https://openalex.org/W4292995118","https://openalex.org/W4392923480","https://openalex.org/W4399187206","https://openalex.org/W6821882943"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0,98],"work":[1],"evaluates":[2],"the":[3,21,24,36,82,121,138],"performance":[4],"of":[5,116,123],"Cyber":[6],"Threat":[7,37],"Intelligence":[8],"(CTI)":[9],"extraction":[10],"methods":[11],"in":[12,103,132],"identifying":[13],"attack":[14,111],"techniques":[15,112],"from":[16],"threat":[17],"reports":[18],"available":[19],"on":[20,143],"web":[22],"using":[23],"MITRE":[25],"ATT&CK":[26,39],"framework.":[27],"We":[28],"analyse":[29],"four":[30],"configurations":[31],"utilising":[32],"state-of-the-art":[33],"tools,":[34],"including":[35,56],"Report":[38],"Mapper":[40],"(TRAM)":[41],"and":[42,60,84,127],"open-source":[43],"Large":[44],"Language":[45],"Models":[46],"(LLMs)":[47],"such":[48],"as":[49],"Llama2.":[50],"Our":[51,118],"findings":[52],"reveal":[53],"significant":[54],"challenges,":[55],"class":[57],"imbalance,":[58],"overfitting,":[59],"domain-specific":[61],"complexity,":[62],"which":[63],"impede":[64],"accurate":[65],"technique":[66],"extraction.":[67],"To":[68],"mitigate":[69],"these":[70],"issues,":[71],"we":[72],"propose":[73],"a":[74,86,91],"novel":[75],"two-step":[76],"pipeline:":[77],"first,":[78],"an":[79,101,114,133],"LLM":[80],"summarises":[81],"reports,":[83],"second,":[85],"retrained":[87],"SciBERT":[88],"model":[89],"processes":[90],"rebalanced":[92],"dataset":[93],"augmented":[94],"with":[95,109],"LLM-generated":[96],"data.":[97],"approach":[99],"achieves":[100],"improvement":[102],"F1-scores":[104],"compared":[105],"to":[106],"baseline":[107],"models,":[108],"several":[110],"surpassing":[113],"F1-score":[115],"0.90.":[117],"contributions":[119],"enhance":[120],"efficiency":[122],"web-based":[124],"CTI":[125],"systems":[126],"support":[128],"collaborative":[129],"cybersecurity":[130],"operations":[131],"interconnected":[134],"digital":[135],"landscape,":[136],"paving":[137],"way":[139],"for":[140],"future":[141],"research":[142],"integrating":[144],"human-AI":[145],"collaboration":[146],"platforms.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
