{"id":"https://openalex.org/W3157482407","doi":"https://doi.org/10.1109/icpr48806.2021.9413237","title":"Verifying the Causes of Adversarial Examples","display_name":"Verifying the Causes of Adversarial Examples","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3157482407","doi":"https://doi.org/10.1109/icpr48806.2021.9413237","mag":"3157482407"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5100688138","display_name":"Honglin Li","orcid":"https://orcid.org/0000-0002-0654-8179"},"institutions":[{"id":"https://openalex.org/I4210126463","display_name":"UK Dementia Research Institute","ror":"https://ror.org/02wedp412","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210126463"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Honglin Li","raw_affiliation_strings":["Care Research and Technology Centre, The UK Dementia Research Institute (UK DRI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Care Research and Technology Centre, The UK Dementia Research Institute (UK DRI)","institution_ids":["https://openalex.org/I4210126463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017360469","display_name":"Yifei Fan","orcid":"https://orcid.org/0000-0002-4762-1010"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifei Fan","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090478829","display_name":"Frieder Ganz","orcid":"https://orcid.org/0000-0002-6140-4805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frieder Ganz","raw_affiliation_strings":["Adobe, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe, Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014124403","display_name":"Anthony Yezzi","orcid":"https://orcid.org/0000-0002-3771-4889"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Yezzi","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056157061","display_name":"Payam Barnaghi","orcid":"https://orcid.org/0000-0001-8591-9638"},"institutions":[{"id":"https://openalex.org/I4210126463","display_name":"UK Dementia Research Institute","ror":"https://ror.org/02wedp412","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210126463"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Payam Barnaghi","raw_affiliation_strings":["Care Research and Technology Centre, The UK Dementia Research Institute (UK DRI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Care Research and Technology Centre, The UK Dementia Research Institute (UK DRI)","institution_ids":["https://openalex.org/I4210126463"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1465,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34683848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1807 1069","issue":null,"first_page":"6750","last_page":"6757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9883999824523926,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9167181253433228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7318865060806274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6306518316268921},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5641465187072754},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5476894378662109},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5412895083427429},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5393111705780029},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5361160635948181},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.519827663898468},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5056509971618652}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9167181253433228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318865060806274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306518316268921},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5641465187072754},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5476894378662109},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5412895083427429},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5393111705780029},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5361160635948181},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.519827663898468},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5056509971618652},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3683667027","display_name":null,"funder_award_id":"W911NF-18-1-0281","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W1964168965","https://openalex.org/W1968896562","https://openalex.org/W2025328853","https://openalex.org/W2064675550","https://openalex.org/W2081219861","https://openalex.org/W2117539524","https://openalex.org/W2118020555","https://openalex.org/W2146200922","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2513314332","https://openalex.org/W2785403003","https://openalex.org/W2794002979","https://openalex.org/W2810611310","https://openalex.org/W2891572479","https://openalex.org/W2906186365","https://openalex.org/W2918967742","https://openalex.org/W2951266961","https://openalex.org/W2963207607","https://openalex.org/W2964153729","https://openalex.org/W2966763031","https://openalex.org/W2970115835","https://openalex.org/W2979693376","https://openalex.org/W2980000166","https://openalex.org/W2983044655","https://openalex.org/W3004684240","https://openalex.org/W3021492942","https://openalex.org/W3037939899","https://openalex.org/W3118608800","https://openalex.org/W4288359148","https://openalex.org/W4288618201","https://openalex.org/W4289549563","https://openalex.org/W4295803779","https://openalex.org/W6656529242","https://openalex.org/W6684191040","https://openalex.org/W6752654261","https://openalex.org/W6757253739","https://openalex.org/W6761839128"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2482350142","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"The":[0,80],"robustness":[1],"of":[2,46,63,66,83,93,100,112,116,172],"neural":[3,126],"networks":[4,127],"is":[5],"challenged":[6],"by":[7,28],"adversarial":[8,47,67,84,173],"examples":[9,48,68,85],"that":[10,137],"contain":[11],"almost":[12],"imperceptible":[13],"perturbations":[14],"to":[15,21,141,166],"inputs":[16],"which":[17,175],"mislead":[18],"a":[19,34,61],"classifier":[20],"incorrect":[22],"outputs":[23],"in":[24,32,176],"high":[25,155],"confidence.":[26,157],"Limited":[27],"the":[29,44,94,98,150,169],"extreme":[30],"difficulty":[31],"examining":[33],"high-dimensional":[35],"image":[36],"space":[37],"thoroughly,":[38],"research":[39],"on":[40,52,181],"explaining":[41],"and":[42,54,69,91,119,129,146],"justifying":[43],"causes":[45,65,82,145,171],"falls":[49],"behind":[50],"studies":[51,165],"attacks":[53],"defenses.":[55],"In":[56],"this":[57,160],"paper,":[58],"we":[59],"present":[60],"collection":[62],"potential":[64],"verify":[70],"(or":[71],"partially":[72],"verify)":[73],"them":[74],"through":[75],"carefully":[76],"-designed":[77],"controlled":[78],"experiments.":[79],"major":[81],"include":[86],"model":[87],"linearity,":[88],"one-sum":[89],"constraint,":[90],"geometry":[92],"categories.":[95],"To":[96],"control":[97],"effect":[99],"those":[101],"causes,":[102],"multiple":[103],"techniques":[104],"are":[105],"applied":[106],"such":[107],"as":[108],"L2":[109],"normalization,":[110],"replacement":[111],"loss":[113],"functions,":[114],"construction":[115],"reference":[117],"datasets,":[118],"novel":[120],"models":[121],"using":[122],"multi-layer":[123],"perceptron":[124],"probabilistic":[125],"(MLP-PNN)":[128],"density":[130],"estimation":[131],"(DE).":[132],"Our":[133],"experiment":[134],"results":[135],"show":[136],"geometric":[138],"factors":[139,148],"tend":[140],"be":[142],"more":[143,164,183],"direct":[144],"statistical":[147],"magnify":[149],"phenomenon,":[151],"especially":[152],"for":[153],"assigning":[154],"prediction":[156],"We":[158],"believe":[159],"paper":[161],"will":[162],"inspire":[163],"rigorously":[167],"investigate":[168],"root":[170],"examples,":[174],"turn":[177],"provide":[178],"useful":[179],"guidance":[180],"designing":[182],"robust":[184],"models.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}