{"id":"https://openalex.org/W7143622931","doi":"https://doi.org/10.22364/bjmc.2026.14.1.07","title":"Evaluating Binary, Perlin Noise, and Physical Mark of Backdoor Attacks in Medical Image Classification","display_name":"Evaluating Binary, Perlin Noise, and Physical Mark of Backdoor Attacks in Medical Image Classification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7143622931","doi":"https://doi.org/10.22364/bjmc.2026.14.1.07"},"language":null,"primary_location":{"id":"doi:10.22364/bjmc.2026.14.1.07","is_oa":true,"landing_page_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","pdf_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","source":{"id":"https://openalex.org/S4210204244","display_name":"Baltic Journal of Modern Computing","issn_l":"2255-8942","issn":["2255-8942","2255-8950"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310314132","host_organization_name":"Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of Universi","host_organization_lineage":["https://openalex.org/P4310314132"],"host_organization_lineage_names":["Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of Universi"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Baltic Journal of Modern Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004219935","display_name":"Art\u016brs \u0145iku\u013cins","orcid":"https://orcid.org/0000-0002-3356-4764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arturs Nikulins","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091399998","display_name":"Inese Po\u013caka","orcid":"https://orcid.org/0000-0002-9892-7765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Inese Po\u013caka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089677989","display_name":"Kaspars Sudars","orcid":"https://orcid.org/0000-0002-9110-9065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaspars Sudars","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35245266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8345999717712402,"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":0.8345999717712402,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.04470000043511391,"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"}},{"id":"https://openalex.org/T10828","display_name":"Biometric Identification and Security","score":0.010499999858438969,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.8744999766349792},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41830000281333923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41190001368522644},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3375000059604645},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.2851000130176544}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.8744999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6123999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.554099977016449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.24539999663829803},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23639999330043793}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.22364/bjmc.2026.14.1.07","is_oa":true,"landing_page_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","pdf_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","source":{"id":"https://openalex.org/S4210204244","display_name":"Baltic Journal of Modern Computing","issn_l":"2255-8942","issn":["2255-8942","2255-8950"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310314132","host_organization_name":"Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of Universi","host_organization_lineage":["https://openalex.org/P4310314132"],"host_organization_lineage_names":["Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of Universi"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Baltic Journal of Modern Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.22364/bjmc.2026.14.1.07","is_oa":true,"landing_page_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","pdf_url":"https://doi.org/10.22364/bjmc.2026.14.1.07","source":{"id":"https://openalex.org/S4210204244","display_name":"Baltic Journal of Modern Computing","issn_l":"2255-8942","issn":["2255-8942","2255-8950"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310314132","host_organization_name":"Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of Universi","host_organization_lineage":["https://openalex.org/P4310314132"],"host_organization_lineage_names":["Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of Universi"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Baltic Journal of Modern Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1314581055","display_name":null,"funder_award_id":"5.2.1.1","funder_id":"https://openalex.org/F4320324128","funder_display_name":"R\u012bgas Tehnisk\u0101 Universit\u0101te"},{"id":"https://openalex.org/G5420584630","display_name":null,"funder_award_id":"0/2/24/I/CFLA/003","funder_id":"https://openalex.org/F4320324128","funder_display_name":"R\u012bgas Tehnisk\u0101 Universit\u0101te"}],"funders":[{"id":"https://openalex.org/F4320324128","display_name":"R\u012bgas Tehnisk\u0101 Universit\u0101te","ror":"https://ror.org/00twb6c09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7143622931.pdf","grobid_xml":"https://content.openalex.org/works/W7143622931.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"three":[3],"distinct":[4],"types":[5,44],"of":[6,12,45,86,119,130,150,174,195],"backdoor":[7,52,56,136],"attacks":[8],"in":[9,62,78,184,215],"the":[10,29,35,58,84,101,114,117,131,151,175,192,199,208],"context":[11],"medical":[13,63,185,196,216],"imaging":[14,186],"datasets,":[15,187],"specifically":[16],"focusing":[17],"on":[18],"ISIC":[19],"and":[20,38,76,122,144,206],"Medical":[21],"Decathlon":[22],"Brain":[23],"Tumours,":[24],"with":[25],"experiments":[26],"conducted":[27],"using":[28,142],"ResNet":[30],"architecture,":[31],"we":[32],"also":[33],"used":[34],"transformer":[36],"ViT-B/16":[37],"EfficientNet-B0":[39],"to":[40,70,126,156,180],"demonstrate":[41,167],"that":[42,91,168],"different":[43],"architectures":[46],"can":[47,161],"likewise":[48],"be":[49],"affected.The":[50],"first":[51],"type":[53,82,99],"-the":[54],"binary":[55],"-exploits":[57],"consistent":[59],"black":[60],"background":[61],"images":[64],"by":[65,191,203],"altering":[66],"all":[67],"zero-pixel":[68],"values":[69],"ones,":[71],"making":[72],"it":[73],"particularly":[74],"effective":[75,182],"stealthy":[77],"this":[79,204],"domain.The":[80],"second":[81],"involves":[83],"use":[85],"Perlin":[87],"noise,":[88],"a":[89,139,188],"perturbation":[90],"subtly":[92],"alters":[93],"image":[94],"data":[95,177],"without":[96],"detection.The":[97],"third":[98],"is":[100,178],"physical":[102],"mark":[103],"backdoor,":[104],"where":[105],"intentional":[106],"or":[107],"unintentional":[108],"markers":[109],"serve":[110],"as":[111,170,172],"triggers":[112],"for":[113,211],"attack.We":[115],"assess":[116],"impact":[118],"these":[120],"backdoors":[121,183],"employ":[123],"Explainable":[124],"AI":[125,217],"provide":[127],"human-understandable":[128],"visualizations":[129],"model's":[132],"focus,":[133],"highlighting":[134],"potential":[135],"locations.We":[137],"perform":[138],"quantitative":[140],"evaluation":[141],"deletion":[143],"insertion":[145],"curves":[146],"alongside":[147],"qualitative":[148],"analysis":[149],"XAI":[152,159],"maps,":[153],"allowing":[154],"us":[155],"conclude":[157],"whether":[158],"methods":[160],"reliably":[162],"reveal":[163],"such":[164],"triggers.Our":[165],"findings":[166],"poisoning":[169],"little":[171],"10%":[173],"training":[176],"sufficient":[179],"implant":[181],"vulnerability":[189],"amplified":[190],"fixed":[193],"format":[194],"data.We":[197],"discuss":[198],"significant":[200],"risks":[201],"posed":[202],"threat":[205],"emphasize":[207],"urgent":[209],"need":[210],"robust":[212],"security":[213],"measures":[214],"systems.":[218]},"counts_by_year":[],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2026-04-01T00:00:00"}