{"id":"https://openalex.org/W7126185900","doi":"https://doi.org/10.1109/raid67961.2025.00025","title":"Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks","display_name":"Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7126185900","doi":"https://doi.org/10.1109/raid67961.2025.00025"},"language":null,"primary_location":{"id":"doi:10.1109/raid67961.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/raid67961.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Symposium on Research in Attacks, Intrusions and Defenses (RAID)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5124405483","display_name":"Jiachen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiachen Li","raw_affiliation_strings":["RMIT University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012701826","display_name":"Bang Ye Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bang Wu","raw_affiliation_strings":["RMIT University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101916405","display_name":"Xiaoyu Xia","orcid":"https://orcid.org/0000-0003-3974-8764"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoyu Xia","raw_affiliation_strings":["RMIT University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124395150","display_name":"Xiaoning Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoning Liu","raw_affiliation_strings":["RMIT University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124344495","display_name":"Xun Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xun Yi","raw_affiliation_strings":["RMIT University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021983750","display_name":"Xiuzhen Zhang","orcid":"https://orcid.org/0000-0001-5558-3790"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiuzhen Zhang","raw_affiliation_strings":["RMIT University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Melbourne,Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":3.4704,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94210126,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.7269999980926514,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.7269999980926514,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.16269999742507935,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.046799998730421066,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.9944999814033508},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.6953999996185303},{"id":"https://openalex.org/keywords/neuromorphic-engineering","display_name":"Neuromorphic engineering","score":0.5587000250816345},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4934999942779541},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3871000111103058},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37689998745918274}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9944999814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001000046730042},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.6953999996185303},{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.5587000250816345},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4893999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4009000062942505},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3871000111103058},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/raid67961.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/raid67961.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Symposium on Research in Attacks, Intrusions and Defenses (RAID)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7617473602294922}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1536018596","https://openalex.org/W1972053684","https://openalex.org/W1973207880","https://openalex.org/W2006370340","https://openalex.org/W2010315761","https://openalex.org/W2031783473","https://openalex.org/W2034996255","https://openalex.org/W2130459697","https://openalex.org/W2132870234","https://openalex.org/W2513853720","https://openalex.org/W2619510810","https://openalex.org/W2745933219","https://openalex.org/W2798878556","https://openalex.org/W2807363941","https://openalex.org/W2934843808","https://openalex.org/W2942091739","https://openalex.org/W2962804204","https://openalex.org/W2984844508","https://openalex.org/W2986013765","https://openalex.org/W2998119008","https://openalex.org/W3010216907","https://openalex.org/W3014020978","https://openalex.org/W3039515597","https://openalex.org/W3042368254","https://openalex.org/W3074128044","https://openalex.org/W3088319946","https://openalex.org/W3102040318","https://openalex.org/W3107337211","https://openalex.org/W3121127024","https://openalex.org/W3198957722","https://openalex.org/W3201870057","https://openalex.org/W3204619801","https://openalex.org/W3214253320","https://openalex.org/W4206742934","https://openalex.org/W4214564822","https://openalex.org/W4231081240","https://openalex.org/W4238614602","https://openalex.org/W4308410091","https://openalex.org/W4385679845","https://openalex.org/W4386065754","https://openalex.org/W4387409844","https://openalex.org/W4391725253","https://openalex.org/W4391725281","https://openalex.org/W4402288683","https://openalex.org/W4405182564","https://openalex.org/W4408750087","https://openalex.org/W4411337730"],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"Neural":[1,21,154],"Networks":[2,22],"(SNNs)":[3],"have":[4],"attracted":[5],"significant":[6,65],"attention":[7],"from":[8,191,197,269],"the":[9,28,73,112,121,126,136,163,167,170,181,186,192,204,209,222,264,273],"research":[10,66],"community":[11],"due":[12,56],"to":[13,19,57,75,100,128,140,179,229,278],"their":[14],"high":[15],"energy":[16],"efficiency":[17],"compared":[18],"Artificial":[20],"(ANNs).":[23],"However,":[24],"rare":[25],"studies":[26],"on":[27,234],"security":[29],"of":[30,116,125,135],"SNNs":[31,84,105,127,230],"were":[32],"conducted,":[33],"especially":[34],"in":[35,53,83,104,120,175,203,248,258,296],"backdoor":[36,43,77,90,182,218],"attacks.":[37],"Existing":[38],"defense":[39],"methods":[40],"for":[41,79,289],"ANN":[42],"attacks":[44,82,252],"either":[45],"perform":[46],"poorly":[47],"or":[48,138,283],"can":[49],"be":[50],"easily":[51],"bypassed":[52],"SNN":[54],"scenarios":[55],"SNNs\u2019":[58],"event-driven":[59],"and":[60,85,149,253],"temporal":[61,117,193],"dependency":[62],"characteristics,":[63],"posing":[64],"challenges.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,144,211],"identify":[72],"blockers":[74,103],"existing":[76],"defenses":[78],"defending":[80],"against":[81],"propose":[86],"an":[87,290],"unsupervised":[88],"post-training":[89],"detection":[91,288],"method":[92],"named":[93,153],"Temporal":[94],"Membrane":[95],"Potential":[96],"Backdoor":[97,157],"Detection":[98],"(TMPBD)":[99],"address":[101],"those":[102],"with":[106,216,231,280,287],"neuromorphic":[107,236],"data.":[108,142],"Specifically,":[109],"TMPBD":[110,243],"employs":[111],"maximum":[113],"margin":[114],"statistic":[115],"membrane":[118,194],"potential":[119,195],"last":[122],"spiking":[123],"layer":[124],"detect":[129],"attack":[130,137,219,227,255,265,276],"target":[131,256],"labels":[132,257],"without":[133,293],"knowledge":[134],"access":[139],"any":[141],"Moreover,":[143],"also":[145],"design":[146],"a":[147,198,213],"practical":[148],"robust":[150],"mitigation":[151,282],"mechanism":[152],"Dendrites":[155],"Suppression":[156],"Mitigation":[158],"(NDSBM).":[159],"NDSBM":[160,262],"dually":[161],"clamps":[162],"neural":[164],"dendrites,":[165],"i.e.,":[166],"weights":[168],"connecting":[169],"first":[171],"two":[172],"convolution":[173,177],"layers":[174],"each":[176],"block":[178],"limit":[180],"effect,":[183],"while":[184],"preserving":[185],"benign":[187],"model":[188],"behaviors":[189],"learned":[190],"obtained":[196],"small,":[199],"clean,":[200],"unlabeled":[201],"dataset":[202],"same":[205],"domain.":[206],"To":[207],"evaluate":[208],"performance,":[210],"conduct":[212],"comprehensive":[214],"evaluation":[215],"multiple":[217],"techniques,":[220],"including":[221],"SOTA":[223],"input-aware":[224],"dynamic":[225,250,274],"trigger":[226,251,275],"dedicated":[228],"clean":[232,297],"models":[233],"three":[235],"benchmark":[237,260],"datasets.":[238,261],"The":[239],"results":[240],"demonstrated":[241],"that":[242],"achieves":[244],"100%":[245,270],"prediction":[246],"accuracy":[247],"detecting":[249],"associating":[254],"all":[259],"lowered":[263],"success":[266],"rate":[267],"(ASR)":[268],"caused":[271],"by":[272],"down":[277],"8.44%":[279],"only":[281],"2.81%":[284],"when":[285],"combined":[286],"end-to-end":[291],"pipeline":[292],"performance":[294],"degradation":[295],"accuracy.":[298]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-01T00:00:00"}