{"id":"https://openalex.org/W4416251597","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227981","title":"DeBUGCN - Detecting Backdoors in CNNs Using Graph Convolutional Networks","display_name":"DeBUGCN - Detecting Backdoors in CNNs Using Graph Convolutional Networks","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251597","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227981"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5070506075","display_name":"A. Vartak","orcid":"https://orcid.org/0000-0003-1507-1365"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akash Vartak","raw_affiliation_strings":["University of Maryland, Baltimore County,Baltimore,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County,Baltimore,USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040814039","display_name":"Khondoker Murad Hossain","orcid":null},"institutions":[{"id":"https://openalex.org/I36344538","display_name":"Albany Molecular Research (United States)","ror":"https://ror.org/03y76pe29","country_code":"US","type":"company","lineage":["https://openalex.org/I36344538"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khondoker Murad Hossain","raw_affiliation_strings":["GE Aerospace Research,Albany,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE Aerospace Research,Albany,USA","institution_ids":["https://openalex.org/I36344538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114778025","display_name":"Tim Oates","orcid":"https://orcid.org/0000-0002-8655-747X"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Oates","raw_affiliation_strings":["University of Maryland, Baltimore County,Baltimore,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County,Baltimore,USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9440000057220459,"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":0.9440000057220459,"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":0.01640000008046627,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00930000003427267,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8901000022888184},{"id":"https://openalex.org/keywords/trojan","display_name":"Trojan","score":0.802299976348877},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7235999703407288},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6133000254631042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5853999853134155},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5674999952316284},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.54339998960495},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43970000743865967}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.8901000022888184},{"id":"https://openalex.org/C174333608","wikidata":"https://www.wikidata.org/wiki/Q19635","display_name":"Trojan","level":2,"score":0.802299976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407000064849854},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7235999703407288},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6133000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6132000088691711},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.54339998960495},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C193435613","wikidata":"https://www.wikidata.org/wiki/Q2997928","display_name":"Connected component","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2907492528","https://openalex.org/W2934843808","https://openalex.org/W2935842115","https://openalex.org/W2962810718","https://openalex.org/W2986013765","https://openalex.org/W3034258347","https://openalex.org/W3092005433","https://openalex.org/W3109235236","https://openalex.org/W3114686421","https://openalex.org/W3140377724","https://openalex.org/W3169509819","https://openalex.org/W3175215793","https://openalex.org/W3198381997","https://openalex.org/W3204619801","https://openalex.org/W4230172274","https://openalex.org/W4283317927","https://openalex.org/W4296558692","https://openalex.org/W4402157186"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2,37],"(DNNs)":[3],"are":[4],"becoming":[5],"commonplace":[6],"in":[7],"critical":[8],"applications,":[9],"making":[10],"their":[11],"susceptibility":[12],"to":[13,63],"backdoor":[14,27],"(trojan)":[15],"attacks":[16],"a":[17,25,61,65,77,84,126],"significant":[18],"problem.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,99],"introduce":[24],"novel":[26],"attack":[28],"detection":[29,165],"pipeline,":[30,98],"detecting":[31],"attacked":[32],"models":[33,107],"using":[34,123],"graph":[35,66],"convolution":[36],"(DeBUGCN).":[38],"To":[39,92],"the":[40,47,57,90,94,109,119,136,147],"best":[41],"of":[42,50,60,68,96,102,141,152],"our":[43,97,131,157],"knowledge,":[44],"ours":[45],"is":[46,73,133,168],"first":[48],"use":[49,56,129],"GCNs":[51],"for":[52,89],"trojan":[53,85,164],"detection.":[54],"We":[55],"static":[58],"weights":[59],"DNN":[62,120],"create":[64],"structure":[67],"its":[69],"layers.":[70],"A":[71],"GCN":[72],"then":[74],"used":[75],"as":[76],"binary":[78],"classifier":[79],"on":[80,108,135,155,159],"these":[81],"graphs,":[82],"yielding":[83],"or":[86],"clean":[87,103],"determination":[88],"DNN.":[91],"demonstrate":[93],"efficacy":[95],"train":[100],"hundreds":[101],"and":[104,113,117,149,170],"trojaned":[105],"CNN":[106,143],"MNIST":[110],"handwritten":[111],"digits":[112],"CIFAR-10":[114],"image":[115],"datasets,":[116],"show":[118],"classification":[121],"results":[122,158],"DeBUGCN.":[124,153],"For":[125],"true":[127],"In-the-Wild":[128],"case,":[130],"pipeline":[132],"evaluated":[134],"TrojAI":[137],"dataset":[138],"which":[139],"consists":[140],"various":[142],"architectures,":[144],"thus":[145],"showing":[146],"robustness":[148],"model-agnostic":[150],"behaviour":[151],"Furthermore,":[154],"comparing":[156],"several":[160],"datasets":[161],"with":[162],"state-of-the-art":[163],"algorithms,":[166],"DeBUGCN":[167],"faster":[169],"more":[171],"accurate.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}