{"id":"https://openalex.org/W3006738123","doi":"https://doi.org/10.1109/milcom55135.2022.10017763","title":"Tensorshield: Tensor-based Defense Against Adversarial Attacks on Images","display_name":"Tensorshield: Tensor-based Defense Against Adversarial Attacks on Images","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W3006738123","doi":"https://doi.org/10.1109/milcom55135.2022.10017763","mag":"3006738123"},"language":"en","primary_location":{"id":"doi:10.1109/milcom55135.2022.10017763","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/milcom55135.2022.10017763","pdf_url":null,"source":{"id":"https://openalex.org/S4363608114","display_name":"MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM)","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/A5078317187","display_name":"Negin Entezari","orcid":"https://orcid.org/0000-0001-8908-7832"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Negin Entezari","raw_affiliation_strings":["University of California,Riverside","University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Riverside","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054849323","display_name":"Evangelos E. Papalexakis","orcid":"https://orcid.org/0000-0002-3411-8483"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos E. Papalexakis","raw_affiliation_strings":["University of California,Riverside","University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Riverside","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"999","last_page":"1004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.998199999332428,"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":0.998199999332428,"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":0.9878000020980835,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7733071446418762},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6775389909744263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6481258273124695},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6385471820831299},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6380410194396973},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.6186755895614624},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5529638528823853},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5352469086647034},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4864215850830078},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4425922632217407},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4354332983493805},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.42580246925354004},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41447919607162476},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39094966650009155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11484232544898987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733071446418762},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6775389909744263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481258273124695},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6385471820831299},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6380410194396973},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.6186755895614624},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5529638528823853},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5352469086647034},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4864215850830078},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4425922632217407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4354332983493805},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.42580246925354004},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41447919607162476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39094966650009155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11484232544898987},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/milcom55135.2022.10017763","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/milcom55135.2022.10017763","pdf_url":null,"source":{"id":"https://openalex.org/S4363608114","display_name":"MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM)","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":55,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1686810756","https://openalex.org/W1945616565","https://openalex.org/W1959608418","https://openalex.org/W1963826206","https://openalex.org/W1993482030","https://openalex.org/W2024165284","https://openalex.org/W2108598243","https://openalex.org/W2121739212","https://openalex.org/W2180612164","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2230740169","https://openalex.org/W2460937040","https://openalex.org/W2467604901","https://openalex.org/W2528907418","https://openalex.org/W2528914598","https://openalex.org/W2544822491","https://openalex.org/W2613144983","https://openalex.org/W2810611310","https://openalex.org/W2905483182","https://openalex.org/W2912794670","https://openalex.org/W2950468330","https://openalex.org/W2962700793","https://openalex.org/W2962872506","https://openalex.org/W2962878175","https://openalex.org/W2963001136","https://openalex.org/W2963178695","https://openalex.org/W2963207607","https://openalex.org/W2963268689","https://openalex.org/W2963542245","https://openalex.org/W2963744840","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2998122931","https://openalex.org/W4293846201","https://openalex.org/W4300725094","https://openalex.org/W6637162671","https://openalex.org/W6637373629","https://openalex.org/W6640425456","https://openalex.org/W6640963894","https://openalex.org/W6685777803","https://openalex.org/W6689238212","https://openalex.org/W6713134421","https://openalex.org/W6720208624","https://openalex.org/W6725195833","https://openalex.org/W6729203000","https://openalex.org/W6734787559","https://openalex.org/W6737432490","https://openalex.org/W6738693630","https://openalex.org/W6739868092","https://openalex.org/W6745272055","https://openalex.org/W6757037778","https://openalex.org/W6758796156"],"related_works":["https://openalex.org/W3046843850","https://openalex.org/W2963115223","https://openalex.org/W2915754718","https://openalex.org/W4299822940","https://openalex.org/W2279398222","https://openalex.org/W2962700793","https://openalex.org/W4206826928","https://openalex.org/W2981169515","https://openalex.org/W4379255972","https://openalex.org/W4383955378"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"demonstrated":[3],"that":[4,100],"machine":[5,38],"learning":[6,39],"approaches":[7],"like":[8],"deep":[9,33],"neural":[10,34],"networks":[11],"(DNNs)":[12],"are":[13,26],"easily":[14],"fooled":[15],"by":[16,122,146],"adversarial":[17,62,120,153],"attacks.":[18,63],"Subtle":[19],"and":[20],"imperceptible":[21],"perturbations":[22,71],"of":[23,32,67,78,98,130],"the":[24,30,65,75,79,133,141],"data":[25],"able":[27],"to":[28,57,93],"change":[29],"result":[31],"networks.":[35],"Leveraging":[36],"vulnerable":[37],"methods":[40],"raises":[41],"many":[42],"concerns,":[43],"especially":[44],"in":[45,74],"domains":[46],"where":[47],"security":[48],"is":[49,55],"an":[50],"important":[51],"factor.":[52],"Therefore,":[53],"it":[54],"crucial":[56],"design":[58],"defense":[59,108,138],"mechanisms":[60],"against":[61,119,148],"For":[64],"task":[66],"image":[68],"classification,":[69],"unnoticeable":[70],"mostly":[72],"occur":[73],"high-frequency":[76,104],"spectrum":[77],"image.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"utilize":[85],"tensor":[86],"decomposition":[87],"techniques":[88],"as":[89],"a":[90,95,107],"preprocessing":[91],"step":[92],"find":[94],"low-rank":[96],"approximation":[97],"images":[99,131],"can":[101],"significantly":[102],"discard":[103],"perturbations.":[105],"Recently":[106],"framework":[109],"called":[110],"Shield":[111,145],"[1]":[112],"could":[113],"\u201cvaccinate\u201d":[114],"Convolutional":[115],"Neural":[116],"Networks":[117],"(CNN)":[118],"examples":[121],"performing":[123],"random-quality":[124],"JPEG":[125],"compressions":[126],"on":[127,132],"local":[128],"patches":[129],"ImageNet":[134],"dataset.":[135],"Our":[136],"tensor-based":[137],"mechanism":[139],"outperforms":[140],"SLQ":[142],"method":[143],"from":[144],"14%":[147],"Fast":[149],"Gradient":[150],"Descent":[151],"(FGSM)":[152],"attacks,":[154],"while":[155],"maintaining":[156],"comparable":[157],"speed.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}