{"id":"https://openalex.org/W7154407511","doi":"https://doi.org/10.48550/arxiv.2604.10933","title":"QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits","display_name":"QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154407511","doi":"https://doi.org/10.48550/arxiv.2604.10933"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.10933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133625911","display_name":"Navid Azimi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azimi, Navid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019711001","display_name":"Aditya Prakash","orcid":"https://orcid.org/0000-0002-5961-8222"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prakash, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133584615","display_name":"Yao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133559658","display_name":"Li Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10020","display_name":"Quantum Information and Cryptography","score":0.25189998745918274,"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/T10020","display_name":"Quantum Information and Cryptography","score":0.25189998745918274,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.24330000579357147,"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.18310000002384186,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/modular-design","display_name":"Modular design","score":0.6090999841690063},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5558000206947327},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.551800012588501},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5358999967575073},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5054000020027161},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5002999901771545},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.42660000920295715},{"id":"https://openalex.org/keywords/hybrid-neural-network","display_name":"Hybrid neural network","score":0.38609999418258667},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35409998893737793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430999875068665},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6090999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5708000063896179},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.551800012588501},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.42660000920295715},{"id":"https://openalex.org/C2779990667","wikidata":"https://www.wikidata.org/wiki/Q5953266","display_name":"Hybrid neural network","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C121040770","wikidata":"https://www.wikidata.org/wiki/Q215675","display_name":"Quantum entanglement","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.2508000135421753},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.10933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1,28,48],"networks":[2],"remain":[3],"highly":[4,128],"vulnerable":[5,129],"to":[6,33,130,169],"adversarial":[7,36,131,156,171,197],"perturbations,":[8],"limiting":[9],"their":[10],"reliability":[11],"in":[12,211],"security-":[13],"and":[14,76,99,107,117,196,207,213],"safety-critical":[15,214],"applications.":[16,215],"To":[17],"address":[18],"this":[19],"challenge,":[20],"we":[21],"introduce":[22],"QShield,":[23],"a":[24,45,56,78,82,89,111,152,190,202],"modular":[25,186],"hybrid":[26,79,100,136,161,187],"quantum-classical":[27,101],"network":[29,49],"(HQCNN)":[30],"architecture":[31,162,188],"designed":[32],"enhance":[34],"the":[35,62,104,134,159,165,184],"robustness":[37],"of":[38,114,155,178],"classical":[39,98,125],"deep":[40],"learning":[41,210],"models.":[42],"QShield":[43],"integrates":[44],"conventional":[46],"convolutional":[47],"(CNN)":[50],"backbone":[51],"for":[52,205],"feature":[53],"extraction":[54],"with":[55,138],"quantum":[57,66],"processing":[58],"module":[59],"that":[60,124,183],"encodes":[61],"extracted":[63],"features":[64],"into":[65],"states,":[67],"applies":[68],"structured":[69],"entanglement":[70,139],"operations":[71],"under":[72],"realistic":[73],"noise":[74],"models,":[75],"outputs":[77],"prediction":[80],"through":[81],"dynamically":[83],"weighted":[84],"fusion":[85],"mechanism":[86],"implemented":[87],"via":[88],"lightweight":[90],"multilayer":[91],"perceptron":[92],"(MLP).":[93],"We":[94],"systematically":[95],"evaluate":[96],"both":[97],"models":[102,126,137],"on":[103],"MNIST,":[105],"OrganAMNIST,":[106],"CIFAR-10":[108],"datasets,":[109],"using":[110],"comprehensive":[112],"set":[113],"robustness,":[115,198],"efficiency,":[116],"computational":[118,166],"performance":[119],"metrics.":[120],"Our":[121],"results":[122],"demonstrate":[123],"are":[127],"attacks,":[132],"whereas":[133],"proposed":[135,160,185],"patterns":[140],"maintain":[141],"high":[142],"predictive":[143,194],"accuracy":[144,195],"while":[145],"substantially":[146],"reducing":[147],"attack":[148],"success":[149],"rates":[150],"across":[151],"wide":[153],"range":[154],"attacks.":[157],"Furthermore,":[158],"significantly":[163],"increased":[164],"cost":[167],"required":[168],"generate":[170],"examples,":[172],"thereby":[173],"introducing":[174],"an":[175],"additional":[176],"layer":[177],"defense.":[179],"These":[180],"findings":[181],"indicate":[182],"achieves":[189],"practical":[191],"balance":[192],"between":[193],"positioning":[199],"it":[200],"as":[201],"promising":[203],"approach":[204],"secure":[206],"reliable":[208],"machine":[209],"sensitive":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-15T00:00:00"}