{"id":"https://openalex.org/W4412951530","doi":"https://doi.org/10.32604/cmc.2025.067284","title":"DSGNN: Dual-Shield Defense for Robust Graph Neural Networks","display_name":"DSGNN: Dual-Shield Defense for Robust Graph Neural Networks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412951530","doi":"https://doi.org/10.32604/cmc.2025.067284"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.067284","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.067284","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.2025.067284","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027669717","display_name":"Xiaohan Chen","orcid":"https://orcid.org/0009-0007-5966-402X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaohan Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069916942","display_name":"Yuanfang Chen","orcid":"https://orcid.org/0000-0002-1557-087X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanfang Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108138677","display_name":"Gyu Myoung Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyu Myoung Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107205316","display_name":"No\u00ebl Crespi","orcid":"https://orcid.org/0000-0003-2962-192X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noel Crespi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035300094","display_name":"Pierluigi Siano","orcid":"https://orcid.org/0000-0002-0975-0241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierluigi Siano","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027669717"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11084528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"1","first_page":"1733","last_page":"1750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.991100013256073,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.991100013256073,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9599000215530396,"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/shield","display_name":"Shield","score":0.639467179775238},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.591319739818573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5025429725646973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45385369658470154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34380418062210083},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3265320658683777},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.28007033467292786},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11352553963661194},{"id":"https://openalex.org/keywords/petrology","display_name":"Petrology","score":0.11019226908683777}],"concepts":[{"id":"https://openalex.org/C138081364","wikidata":"https://www.wikidata.org/wiki/Q852013","display_name":"Shield","level":2,"score":0.639467179775238},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.591319739818573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5025429725646973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45385369658470154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34380418062210083},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3265320658683777},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.28007033467292786},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11352553963661194},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.11019226908683777},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.32604/cmc.2025.067284","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.067284","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"},{"id":"pmh:oai:researchonline.ljmu.ac.uk:26785","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401246","display_name":"Liverpool John Moores University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63098007","host_organization_name":"Liverpool John Moores University","host_organization_lineage":["https://openalex.org/I63098007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.067284","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.067284","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":[{"id":"https://metadata.un.org/sdg/7","score":0.4399999976158142,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W191020423","https://openalex.org/W212028160","https://openalex.org/W4388071457","https://openalex.org/W2384581482","https://openalex.org/W4379056371","https://openalex.org/W4224273067","https://openalex.org/W2379865809","https://openalex.org/W2105077694","https://openalex.org/W3130190534","https://openalex.org/W2350739911"],"abstract_inverted_index":{"Graph":[0,125],"Neural":[1,126],"Networks":[2],"(GNNs)":[3],"have":[4],"demonstrated":[5],"outstanding":[6],"capabilities":[7],"in":[8,231],"processing":[9],"graph-structured":[10],"data":[11,71],"and":[12,33,58,82,109,136,150,153,193,212,220],"are":[13,53,85],"increasingly":[14,63],"being":[15],"integrated":[16],"into":[17],"large-scale":[18],"pre-trained":[19],"models,":[20],"such":[21],"as":[22,51],"Large":[23],"Language":[24],"Models":[25],"(LLMs),":[26],"to":[27,55,65,106,145,165,184],"enhance":[28],"structural":[29,135,148],"reasoning,":[30],"knowledge":[31],"retrieval,":[32],"memory":[34],"management.":[35],"The":[36],"expansion":[37],"of":[38,48,112,227],"their":[39],"application":[40],"scope":[41],"imposes":[42],"higher":[43],"requirements":[44],"on":[45],"the":[46,107,123,200,225],"robustness":[47,178],"GNNs.":[49],"However,":[50],"GNNs":[52],"applied":[54],"more":[56,87],"dynamic":[57],"heterogeneous":[59],"environments,":[60],"they":[61],"become":[62],"vulnerable":[64],"real-world":[66,237],"perturbations.":[67,138],"In":[68],"particular,":[69],"graph":[70],"frequently":[72],"encounters":[73],"joint":[74,181],"adversarial":[75,207],"perturbations":[76,182],"that":[77,132,159,173,197],"simultaneously":[78,133],"affect":[79],"both":[80,163],"structures":[81],"features,":[83],"which":[84],"significantly":[86],"challenging":[88],"than":[89],"isolated":[90],"attacks.":[91],"These":[92,222],"disruptions,":[93],"caused":[94],"by":[95],"incomplete":[96],"data,":[97],"malicious":[98],"attacks,":[99],"or":[100],"inherent":[101],"noise,":[102,152],"pose":[103],"substantial":[104],"threats":[105],"stable":[108],"reliable":[110],"performance":[111],"traditional":[113],"GNN":[114,143,234],"models.":[115],"To":[116],"address":[117],"this":[118,120],"issue,":[119],"study":[121],"proposes":[122],"Dual-Shield":[124],"Network":[127],"(DSGNN),":[128],"a":[129,176],"defense":[130],"model":[131],"mitigates":[134],"feature":[137,151],"DSGNN":[139,174,198],"utilizes":[140],"two":[141],"parallel":[142],"channels":[144],"independently":[146],"process":[147],"noise":[149],"introduces":[154],"an":[155],"adaptive":[156],"fusion":[157],"mechanism":[158],"integrates":[160],"information":[161],"from":[162],"pathways":[164],"generate":[166],"robust":[167],"node":[168],"representations.":[169],"Theoretical":[170],"analysis":[171],"demonstrates":[172],"achieves":[175,199],"tighter":[177],"boundary":[179],"under":[180,205],"compared":[183],"conventional":[185],"single-channel":[186],"methods.":[187],"Experimental":[188],"evaluations":[189],"across":[190],"Cora,":[191],"CiteSeer,":[192],"Industry":[194],"datasets":[195],"show":[196],"highest":[201],"average":[202],"classification":[203],"accuracy":[204],"various":[206],"settings,":[208],"reaching":[209],"81.24%,":[210],"71.94%,":[211],"81.66%,":[213],"respectively,":[214],"outperforming":[215],"GNNGuard,":[216],"GCN-Jaccard,":[217],"GCN-SVD,":[218],"RGCN,":[219],"NoisyGNN.":[221],"results":[223],"underscore":[224],"importance":[226],"multi-view":[228],"perturbation":[229],"decoupling":[230],"constructing":[232],"resilient":[233],"models":[235],"for":[236],"applications.":[238]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}