{"id":"https://openalex.org/W2965499658","doi":"https://doi.org/10.1109/ijcnn.2019.8851930","title":"Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding","display_name":"Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2965499658","doi":"https://doi.org/10.1109/ijcnn.2019.8851930","mag":"2965499658"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.12744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008707729","display_name":"Utku \u00d6zbulak","orcid":"https://orcid.org/0000-0003-3084-6034"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Utku Ozbulak","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Belgium","#N#Ghent University#N#"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"#N#Ghent University#N#","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077912411","display_name":"Arnout Van Messem","orcid":"https://orcid.org/0000-0001-8545-7437"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Arnout Van Messem","raw_affiliation_strings":["Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Belgium","#N#Ghent University#N#"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"#N#Ghent University#N#","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029555436","display_name":"Wesley De Neve","orcid":"https://orcid.org/0000-0002-8190-3839"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wesley De Neve","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Belgium","#N#Ghent University#N#"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"#N#Ghent University#N#","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008707729"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08295337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"8"},"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9564999938011169,"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":0.9295802116394043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6954464912414551},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6193145513534546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5704264640808105},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5413645505905151},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5091938376426697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4907742440700531},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.4536019563674927},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.4483824074268341},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43165719509124756},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34530919790267944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3221656084060669},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26457858085632324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1608549952507019},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1200583279132843},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08988097310066223}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9295802116394043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6954464912414551},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6193145513534546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5704264640808105},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5413645505905151},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5091938376426697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4907742440700531},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.4536019563674927},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.4483824074268341},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43165719509124756},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34530919790267944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3221656084060669},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26457858085632324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1608549952507019},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1200583279132843},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08988097310066223},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.12744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.12744","pdf_url":"https://arxiv.org/pdf/1907.12744","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:8632063","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8632063","pdf_url":"https://biblio.ugent.be/publication/8632063/file/8632065.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728119854","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:2965499658","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.12744v1","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:orbi.ulg.ac.be:2268/257832","is_oa":false,"landing_page_url":"https://orbi.uliege.be/handle/2268/257832","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN), 1-8 (2019); International Joint Conference on Neural Networks 2019 (IJCNN), Budapest, Hungary [HU], 2019","raw_type":"peer reviewed"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/265033","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/265033","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary [HU], 14-19 July 2019","raw_type":"info:eu-repo/semantics/conferencePoster"},{"id":"doi:10.48550/arxiv.1907.12744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.12744","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.12744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.12744","pdf_url":"https://arxiv.org/pdf/1907.12744","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2164745409","display_name":null,"funder_award_id":"VLAIO","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320313460","display_name":"Agentschap Innoveren en Ondernemen","ror":"https://ror.org/032xdry56"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320322603","display_name":"Universiteit Gent","ror":"https://ror.org/00cv9y106"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W183625566","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1932198206","https://openalex.org/W1982029035","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2180612164","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2319794630","https://openalex.org/W2611576673","https://openalex.org/W2785604928","https://openalex.org/W2787708942","https://openalex.org/W2963037989","https://openalex.org/W2963207607","https://openalex.org/W2963389226","https://openalex.org/W2963542245","https://openalex.org/W2963564844","https://openalex.org/W2963857521","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2964341766","https://openalex.org/W4232552111","https://openalex.org/W6628973269","https://openalex.org/W6637162671","https://openalex.org/W6637373629","https://openalex.org/W6640425456","https://openalex.org/W6685736903","https://openalex.org/W6685800298","https://openalex.org/W6719080892","https://openalex.org/W6726114608","https://openalex.org/W6729756640","https://openalex.org/W6748475379","https://openalex.org/W6756405315"],"related_works":["https://openalex.org/W2977326717","https://openalex.org/W3046426875","https://openalex.org/W3126538302","https://openalex.org/W2906965747","https://openalex.org/W2970504098","https://openalex.org/W3184325371","https://openalex.org/W2897650178","https://openalex.org/W3012613466","https://openalex.org/W3199405737","https://openalex.org/W2783692467","https://openalex.org/W2809713126","https://openalex.org/W2963417375","https://openalex.org/W3130611678","https://openalex.org/W3132818334","https://openalex.org/W3110934648","https://openalex.org/W2619479788","https://openalex.org/W2978325266","https://openalex.org/W2787970001","https://openalex.org/W2951467133","https://openalex.org/W3046669982"],"abstract_inverted_index":{"Detecting":[0],"adversarial":[1,21,40,60,71,79,100,134,141],"examples":[2,142],"currently":[3],"stands":[4],"as":[5,77,164],"one":[6],"of":[7,14,27,70,86,112,125,140],"the":[8,12,24,39,59,84,87,94,109,113,117,123,126,165,174],"biggest":[9],"challenges":[10],"in":[11,131,143],"field":[13],"deep":[15],"learning.":[16],"Adversarial":[17],"attacks,":[18],"which":[19,73,153],"produce":[20],"examples,":[22,72,80],"increase":[23],"prediction":[25,118],"likelihood":[26],"a":[28,32,147],"target":[29],"class":[30],"for":[31,116,179],"particular":[33],"data":[34,95],"point.":[35],"During":[36],"this":[37,68,104,138,159],"process,":[38],"example":[41,61],"can":[42],"be":[43],"further":[44],"optimized,":[45],"even":[46,62],"when":[47],"it":[48],"has":[49],"already":[50],"been":[51],"wrongly":[52],"classified":[53],"with":[54,158,176],"100%":[55],"confidence,":[56],"thus":[57],"making":[58],"more":[63,129,162],"difficult":[64],"to":[65,76],"detect.":[66],"For":[67],"kind":[69],"we":[74,81,106,145],"refer":[75],"over-optimized":[78,133],"discovered":[82],"that":[83],"logits":[85,124],"model":[88,127],"provide":[89],"solid":[90],"clues":[91],"on":[92,155],"whether":[93],"point":[96],"at":[97],"hand":[98],"is":[99],"or":[101],"genuine.":[102],"In":[103],"context,":[105],"first":[107],"discuss":[108],"masking":[110],"effect":[111],"softmax":[114],"function":[115],"made":[119],"and":[120,149,184,186],"explain":[121],"why":[122],"are":[128],"useful":[130],"detecting":[132],"examples.":[135],"To":[136],"identify":[137],"type":[139],"practice,":[144],"propose":[146],"non-parametric":[148],"computationally":[150],"efficient":[151],"method":[152,160],"relies":[154],"interquartile":[156],"range,":[157],"becoming":[161],"effective":[163],"image":[166],"resolution":[167],"increases.":[168],"We":[169],"support":[170],"our":[171],"observations":[172],"throughout":[173],"paper":[175],"detailed":[177],"experiments":[178],"different":[180],"datasets":[181],"(MNIST,":[182],"CIFAR-10,":[183],"ImageNet)":[185],"several":[187],"architectures.":[188]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}