{"id":"https://openalex.org/W3114556617","doi":"https://doi.org/10.1109/mmsp48831.2020.9287056","title":"Natural Scene Statistics for Detecting Adversarial Examples in Deep Neural Networks","display_name":"Natural Scene Statistics for Detecting Adversarial Examples in Deep Neural Networks","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3114556617","doi":"https://doi.org/10.1109/mmsp48831.2020.9287056","mag":"3114556617"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp48831.2020.9287056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","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/A5029238837","display_name":"Anouar Kherchouche","orcid":null},"institutions":[{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210116811","display_name":"Ecole Nationale Sup\u00e9rieur des T\u00e9l\u00e9communications et des Technologies de l\u2019Information et de la Communication, Abdelhafid Boussouf","ror":"https://ror.org/023rzn231","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210116811"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["DZ","FR"],"is_corresponding":false,"raw_author_name":"Anouar Kherchouche","raw_affiliation_strings":["INSA Rennes, Univ. Rennes, Rennes, France","National Institute of Telecommunications and ICT, Oran, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSA Rennes, Univ. Rennes, Rennes, France","institution_ids":["https://openalex.org/I28221208","https://openalex.org/I56067802"]},{"raw_affiliation_string":"National Institute of Telecommunications and ICT, Oran, Algeria","institution_ids":["https://openalex.org/I4210116811"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055759473","display_name":"Sid Ahmed Fezza","orcid":"https://orcid.org/0000-0001-6453-8588"},"institutions":[{"id":"https://openalex.org/I4210116811","display_name":"Ecole Nationale Sup\u00e9rieur des T\u00e9l\u00e9communications et des Technologies de l\u2019Information et de la Communication, Abdelhafid Boussouf","ror":"https://ror.org/023rzn231","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210116811"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Sid Ahmed Fezza","raw_affiliation_strings":["National Institute of Telecommunications and ICT, Oran, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Telecommunications and ICT, Oran, Algeria","institution_ids":["https://openalex.org/I4210116811"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084205574","display_name":"Wassim Hamidouche","orcid":"https://orcid.org/0000-0002-0143-1756"},"institutions":[{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Wassim Hamidouche","raw_affiliation_strings":["INSA Rennes, Univ. Rennes, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSA Rennes, Univ. Rennes, Rennes, France","institution_ids":["https://openalex.org/I28221208","https://openalex.org/I56067802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031377954","display_name":"Olivier D\u00e9forges","orcid":"https://orcid.org/0000-0003-0750-0959"},"institutions":[{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Deforges","raw_affiliation_strings":["INSA Rennes, Univ. Rennes, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSA Rennes, Univ. Rennes, Rennes, France","institution_ids":["https://openalex.org/I28221208","https://openalex.org/I56067802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":1.0,"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":1.0,"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":0.9861999750137329,"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":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9257670044898987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7558696866035461},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.668592095375061},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6465317010879517},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6305678486824036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.608475923538208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4971206486225128},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45104193687438965},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43923449516296387},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3507327437400818},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0977022647857666}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9257670044898987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558696866035461},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.668592095375061},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6465317010879517},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6305678486824036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.608475923538208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4971206486225128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45104193687438965},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43923449516296387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3507327437400818},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0977022647857666}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp48831.2020.9287056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03083969v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03083969","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), Sep 2020, Tampere, France. pp.1-6, ⟨10.1109/MMSP48831.2020.9287056⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W1982471090","https://openalex.org/W2117539524","https://openalex.org/W2120838001","https://openalex.org/W2153635508","https://openalex.org/W2158162781","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2243397390","https://openalex.org/W2460937040","https://openalex.org/W2528914598","https://openalex.org/W2561975083","https://openalex.org/W2590523583","https://openalex.org/W2594867206","https://openalex.org/W2606529538","https://openalex.org/W2607219512","https://openalex.org/W2611576673","https://openalex.org/W2613144983","https://openalex.org/W2618043096","https://openalex.org/W2774018344","https://openalex.org/W2902071009","https://openalex.org/W2947133760","https://openalex.org/W2963158386","https://openalex.org/W2963178695","https://openalex.org/W2963207607","https://openalex.org/W2963564844","https://openalex.org/W2963695663","https://openalex.org/W2963857521","https://openalex.org/W2964082701","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2986549955","https://openalex.org/W3105009650","https://openalex.org/W4293584023","https://openalex.org/W4293846201","https://openalex.org/W4297573953","https://openalex.org/W4300511536","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6684191040","https://openalex.org/W6685800298","https://openalex.org/W6719080892","https://openalex.org/W6733645847","https://openalex.org/W6734483310","https://openalex.org/W6736207377","https://openalex.org/W6736296761","https://openalex.org/W6737432490","https://openalex.org/W6739868092","https://openalex.org/W6747819456","https://openalex.org/W6756553689","https://openalex.org/W6786165312","https://openalex.org/W6898611122"],"related_works":["https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W4383221314","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W3203790781","https://openalex.org/W4313346231","https://openalex.org/W2738001131","https://openalex.org/W4285785480","https://openalex.org/W2997056298"],"abstract_inverted_index":{"The":[0,113,129],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"have":[5,132],"been":[6,17,117],"adopted":[7],"in":[8],"a":[9,31,50,97,140,150],"wide":[10],"spectrum":[11],"of":[12,53,58,73,88],"applications.":[13],"However,":[14],"it":[15,45],"has":[16,116],"demonstrated":[18],"that":[19,79,99,134],"their":[20],"are":[21,83],"vulnerable":[22],"to":[23,30,48,65,104],"adversarial":[24,68,89,110,122],"examples":[25],"(AEs):":[26],"carefully-crafted":[27],"perturbations":[28,69],"added":[29],"clean":[32],"input":[33,108],"image.":[34],"These":[35],"AEs":[36,54],"fool":[37],"the":[38,56,67,71,86,135],"DNNs":[39],"which":[40],"classify":[41],"them":[42],"incorrectly.":[43],"Therefore,":[44],"is":[46,109],"imperative":[47],"develop":[49],"detection":[51,137,142],"method":[52,115,138],"allowing":[55],"defense":[57],"DNNs.":[59],"In":[60],"this":[61,93],"paper,":[62],"we":[63,95],"propose":[64],"characterize":[66],"through":[70],"use":[72],"natural":[74],"scene":[75,102],"statistics.":[76],"We":[77],"demonstrate":[78],"these":[80,101],"statistical":[81],"properties":[82],"altered":[84],"by":[85],"presence":[87],"perturbations.":[90],"Based":[91],"on":[92,125],"finding,":[94],"design":[96],"classifier":[98],"exploits":[100],"statistics":[103],"determine":[105],"if":[106],"an":[107],"or":[111],"not.":[112],"proposed":[114,136],"evaluated":[118],"against":[119,145],"four":[120],"prominent":[121],"attacks":[123],"and":[124],"three":[126],"standards":[127],"datasets.":[128],"experimental":[130],"results":[131],"shown":[133],"achieves":[139],"high":[141],"accuracy,":[143],"even":[144],"strong":[146],"attacks,":[147],"while":[148],"providing":[149],"low":[151],"false":[152],"positive":[153],"rate.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}