{"id":"https://openalex.org/W4409649247","doi":"https://doi.org/10.32604/cmc.2025.062080","title":"A Study on the Inter-Pretability of Network Attack Prediction Models Based onLight Gradient Boosting Machine (LGBM) and SHapley Additive exPlanations (SHAP)","display_name":"A Study on the Inter-Pretability of Network Attack Prediction Models Based onLight Gradient Boosting Machine (LGBM) and SHapley Additive exPlanations (SHAP)","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409649247","doi":"https://doi.org/10.32604/cmc.2025.062080"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.062080","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.062080","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.062080","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027686111","display_name":"Shuqin Zhang","orcid":"https://orcid.org/0000-0002-0665-6567"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shuqin Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413078","display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0001-8396-3707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102085604","display_name":"Xinyu Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Su","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027686111"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4803,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81779488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"83","issue":"3","first_page":"5781","last_page":"5809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.7856000065803528,"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"}},"topics":[{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.7856000065803528,"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/gradient-boosting","display_name":"Gradient boosting","score":0.7577285766601562},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6683627367019653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5142297148704529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48242315649986267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4421250522136688},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.33704179525375366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2739834189414978},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.11100947856903076}],"concepts":[{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.7577285766601562},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6683627367019653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142297148704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48242315649986267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4421250522136688},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.33704179525375366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2739834189414978},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.11100947856903076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.062080","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.062080","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.062080","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.062080","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2122590816","https://openalex.org/W2129888542","https://openalex.org/W2892859754","https://openalex.org/W2972825102","https://openalex.org/W2981731882","https://openalex.org/W2996061341","https://openalex.org/W3017093935","https://openalex.org/W3121453273","https://openalex.org/W3127461705","https://openalex.org/W3165381529","https://openalex.org/W3198525581","https://openalex.org/W4229071857","https://openalex.org/W4283072185","https://openalex.org/W4296638419","https://openalex.org/W4303700086","https://openalex.org/W4307571902","https://openalex.org/W4391006471","https://openalex.org/W4400400027","https://openalex.org/W4400810536","https://openalex.org/W4403144291","https://openalex.org/W4406529390","https://openalex.org/W4406882703"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3204430031","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W4310224730","https://openalex.org/W2766514146","https://openalex.org/W4289703016","https://openalex.org/W2885516856","https://openalex.org/W3094138326"],"abstract_inverted_index":{"The":[0,180],"methods":[1],"of":[2,34,47,58,62,103,112,121,124,127,133,145,158,167],"network":[3,35,63,93,105,146,186],"attacks":[4],"have":[5],"become":[6],"increasingly":[7],"sophisticated,":[8],"rendering":[9],"traditional":[10],"cybersecurity":[11],"defense":[12,114],"mechanisms":[13],"insufficient":[14],"to":[15,87,139,152,170],"address":[16,55],"novel":[17],"and":[18,40,50,79,98,101,129,174,196,210],"complex":[19],"threats":[20],"effectively.":[21],"In":[22],"recent":[23],"years,":[24],"artificial":[25],"intelligence":[26],"has":[27],"achieved":[28,118],"significant":[29],"progress":[30],"in":[31,91,142],"the":[32,45,56,60,96,110,116,143,154,159,165,171,176,185,201,207],"field":[33],"security.":[36],"However,":[37],"many":[38],"challenges":[39],"issues":[41],"remain,":[42],"particularly":[43],"regarding":[44],"interpretability":[46,61,162,203],"deep":[48],"learning":[49,52],"ensemble":[51],"algorithms.":[53],"To":[54],"challenge":[57],"enhancing":[59],"attack":[64,106,147,187],"prediction":[65,102,172,188],"models,":[66],"this":[67],"paper":[68],"proposes":[69],"a":[70],"method":[71],"that":[72,184],"combines":[73],"Light":[74],"Gradient":[75],"Boosting":[76],"Machine":[77],"(LGBM)":[78],"SHapley":[80],"Additive":[81],"exPlanations":[82],"(SHAP).":[83],"LGBM":[84,192],"is":[85,150],"employed":[86],"model":[88,117,189],"anomalous":[89],"fluctuations":[90],"various":[92],"indicators,":[94],"enabling":[95],"rapid":[97],"accurate":[99],"identification":[100],"potential":[104],"types,":[107],"thereby":[108],"facilitating":[109],"implementation":[111],"timely":[113],"measures,":[115],"an":[119,130],"accuracy":[120,195],"0.977,":[122],"precision":[123],"0.985,":[125],"recall":[126],"0.975,":[128],"F1":[131],"score":[132],"0.979,":[134],"demonstrating":[135],"better":[136],"performance":[137],"compared":[138],"other":[140],"models":[141],"domain":[144],"prediction.":[148],"SHAP":[149],"utilized":[151],"analyze":[153],"black-box":[155],"decision-making":[156],"process":[157],"model,":[160],"providing":[161],"by":[163],"quantifying":[164],"contribution":[166],"each":[168],"feature":[169],"results":[173,182],"elucidating":[175],"relationships":[177],"between":[178],"features.":[179],"experimental":[181],"demonstrate":[183],"based":[190],"on":[191],"exhibits":[193],"superior":[194],"outstanding":[197],"predictive":[198],"capabilities.":[199],"Moreover,":[200],"SHAP-based":[202],"analysis":[204],"significantly":[205],"improves":[206],"model\u2019s":[208],"transparency":[209],"interpretability.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}