{"id":"https://openalex.org/W7123352844","doi":"https://doi.org/10.1109/tifs.2026.3653553","title":"Cracking the Code of Backdoor Attacks With Confidence Consistency","display_name":"Cracking the Code of Backdoor Attacks With Confidence Consistency","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123352844","doi":"https://doi.org/10.1109/tifs.2026.3653553"},"language":null,"primary_location":{"id":"doi:10.1109/tifs.2026.3653553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3653553","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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":null,"display_name":"Zhen Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Zhuang","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103096617","display_name":"Yijian Ding","orcid":"https://orcid.org/0009-0006-0088-3108"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijian Ding","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102865973","display_name":"Shuyu Zheng","orcid":"https://orcid.org/0009-0006-6432-4209"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyu Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122881459","display_name":"Jun Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Shao","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122906927","display_name":"Donghai Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghai Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122854304","display_name":"Huiyan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyan Wang","raw_affiliation_strings":["School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75059550"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08678044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"1228","last_page":"1240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9714000225067139,"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":0.9714000225067139,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.006399999838322401,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.0044999998062849045,"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/backdoor","display_name":"Backdoor","score":0.9897000193595886},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7099000215530396},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.541700005531311},{"id":"https://openalex.org/keywords/lock","display_name":"Lock (firearm)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43380001187324524},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.3653999865055084}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9897000193595886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346999883651733},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7099000215530396},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.541700005531311},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.301800012588501},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2026.3653553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3653553","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5917242169380188,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3571229214","display_name":null,"funder_award_id":"2372040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6370682590","display_name":null,"funder_award_id":"TAGI2-A-2024-0004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7128651859","display_name":null,"funder_award_id":"62372040","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G77447760","display_name":null,"funder_award_id":"2272413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8104162393","display_name":null,"funder_award_id":"62272413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2753783305","https://openalex.org/W2807363941","https://openalex.org/W2934843808","https://openalex.org/W2942091739","https://openalex.org/W2970335439","https://openalex.org/W2971661634","https://openalex.org/W2986013765","https://openalex.org/W2990270730","https://openalex.org/W2996800219","https://openalex.org/W3016970897","https://openalex.org/W3096024389","https://openalex.org/W3107337211","https://openalex.org/W3114686421","https://openalex.org/W3212158867","https://openalex.org/W4214537185","https://openalex.org/W4214680449","https://openalex.org/W4251660045","https://openalex.org/W4312569687","https://openalex.org/W4324007135","https://openalex.org/W4386072159","https://openalex.org/W4386076050","https://openalex.org/W4388145338","https://openalex.org/W4402263926","https://openalex.org/W4402264202","https://openalex.org/W4402264250","https://openalex.org/W4402288683","https://openalex.org/W4402716190"],"related_works":[],"abstract_inverted_index":{"It":[0],"is":[1,81,104,155,163],"widely":[2],"believed":[3],"that":[4,39,73,95,295],"increasing":[5],"the":[6,12,60,97,100,125,171,193,216,224,270,282,286,299,312,340],"amount":[7],"of":[8,14,99,127,188,208,227,263,272,288],"training":[9,195,229],"data":[10,162],"enhances":[11],"intelligence":[13],"deep":[15],"learning":[16],"models,":[17],"which":[18,103,130],"in":[19,108,158,211,339],"turn":[20],"heightens":[21],"dependence":[22],"on":[23,239,311],"external":[24,174],"datasets.":[25],"However,":[26],"these":[27,138],"datasets":[28],"are":[29],"susceptible":[30],"to":[31,36,84,122,183,186,214,252,255,304],"adversarial":[32],"poisoning,":[33],"allowing":[34],"attackers":[35],"insert":[37],"backdoors":[38],"trigger":[40],"misclassifications.":[41],"Although":[42],"various":[43],"defense":[44],"strategies":[45],"have":[46,115],"been":[47],"suggested,":[48],"training-phase":[49,150],"defenses":[50],"(TPDs)":[51],"appear":[52],"most":[53,112],"promising,":[54],"as":[55,167],"they":[56],"can":[57],"significantly":[58,179],"lower":[59],"attack":[61,300],"success":[62,301],"rate":[63,302,326,333],"(ASR)":[64,303],"without":[65],"greatly":[66],"impacting":[67],"model":[68,228,238,283],"performance.":[69],"Nevertheless,":[70],"creating":[71],"TPDs":[72],"achieve":[74],"both":[75],"high":[76,116,217],"accuracy":[77],"and":[78,148,265,276,328],"low":[79],"ASR":[80],"challenging":[82],"due":[83],"two":[85],"main":[86],"issues:":[87],"1)":[88],"Many":[89],"solutions":[90,114,190],"require":[91],"additional":[92],"clean":[93,161,175,266,314],"samples":[94,222,267],"match":[96],"distribution":[98],"poisoned":[101,241,256,264,290,318],"dataset,":[102],"not":[105],"always":[106],"practical":[107,134],"real-world":[109],"scenarios;":[110],"2)":[111],"existing":[113,189],"computational":[117,181],"costs,":[118],"sometimes":[119],"requiring":[120],"five":[121],"ten":[123],"times":[124,192],"expense":[126],"standard":[128,194],"training,":[129,284],"severely":[131],"limits":[132],"their":[133],"use.":[135],"To":[136],"tackle":[137],"challenges,":[139],"we":[140,234],"introduce":[141],"Confidence":[142],"Consistency":[143],"Detection":[144],"(CCD),":[145],"an":[146],"efficient":[147],"lightweight":[149],"backdoor":[151,221],"detection":[152,287],"method.":[153],"CCD":[154,178,209,296,320],"particularly":[156],"advantageous":[157],"situations":[159],"where":[160],"scarce":[164],"or":[165],"unavailable,":[166],"it":[168],"completely":[169],"eliminates":[170],"need":[172],"for":[173,230,243],"samples.":[176,257,291],"Moreover,":[177],"reduces":[180,298],"costs":[182],"just":[184],"25%":[185],"50%":[187],"(1.7":[191],"time),":[196],"providing":[197],"a":[198,237,240,244,308,322,329,336],"notable":[199],"improvement":[200],"over":[201],"current":[202],"TPD":[203],"methods.":[204],"The":[205],"core":[206],"innovation":[207],"lies":[210],"its":[212],"ability":[213],"utilize":[215],"confidence":[218,273],"shown":[219],"by":[220,248,268],"during":[223],"early":[225],"stages":[226],"precise":[231],"detection.":[232],"Specifically,":[233],"initially":[235],"train":[236],"dataset":[242],"few":[245],"epochs,":[246],"followed":[247],"intra-class":[249],"loss":[250],"fine-tuning":[251],"increase":[253],"sensitivity":[254],"We":[258],"then":[259],"create":[260],"preliminary":[261],"sets":[262,280],"assessing":[269],"consistency":[271],"variations":[274],"before":[275],"after":[277],"fine-tuning.":[278],"These":[279],"guide":[281],"enabling":[285],"high-confidence":[289],"Extensive":[292],"experiments":[293],"demonstrate":[294],"effectively":[297],"1.43%,":[305],"while":[306],"having":[307],"negligible":[309],"impact":[310],"model\u2019s":[313],"accuracy.":[315],"In":[316],"detecting":[317],"samples,":[319],"achieves":[321],"99%":[323],"true":[324],"positive":[325,332],"(TPR)":[327],"0.033%":[330],"false":[331],"(FPR),":[334],"setting":[335],"new":[337],"benchmark":[338],"field.":[341]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}