{"id":"https://openalex.org/W2893099989","doi":"https://doi.org/10.1145/3319535.3345660","title":"Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks","display_name":"Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks","publication_year":2019,"publication_date":"2019-11-06","ids":{"openalex":"https://openalex.org/W2893099989","doi":"https://doi.org/10.1145/3319535.3345660","mag":"2893099989"},"language":"en","primary_location":{"id":"doi:10.1145/3319535.3345660","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319535.3345660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.00470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kenneth T. Co","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kenneth T. Co","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Luis Mu\u00f1oz-Gonz\u00e1lez","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luis Mu\u00f1oz-Gonz\u00e1lez","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sixte de Maupeou","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sixte de Maupeou","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":null,"display_name":"Emil C. Lupu","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emil C. Lupu","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":3.9059,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94808946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"289"},"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":0.9936000108718872,"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":0.9614999890327454,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9158999919891357},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5756000280380249},{"id":"https://openalex.org/keywords/universality","display_name":"Universality (dynamical systems)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.446399986743927},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4043000042438507},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3898000121116638}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9158999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58160001039505},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5756000280380249},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.48579999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4819999933242798},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3319535.3345660","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319535.3345660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.00470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.00470","pdf_url":"https://arxiv.org/pdf/1810.00470","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:spiral.imperial.ac.uk:10044/1/71700","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/71700","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"26th ACM Conference on Computer and Communications Security","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.00470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.00470","pdf_url":"https://arxiv.org/pdf/1810.00470","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1893133781","https://openalex.org/W1966832848","https://openalex.org/W1976948919","https://openalex.org/W2077205830","https://openalex.org/W2095577883","https://openalex.org/W2117539524","https://openalex.org/W2160815625","https://openalex.org/W2161381512","https://openalex.org/W2169216879","https://openalex.org/W2183341477","https://openalex.org/W2192203593","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2274287116","https://openalex.org/W2399941526","https://openalex.org/W2406556600","https://openalex.org/W2414564754","https://openalex.org/W2506506742","https://openalex.org/W2529714286","https://openalex.org/W2543927648","https://openalex.org/W2570343428","https://openalex.org/W2572504188","https://openalex.org/W2603766943","https://openalex.org/W2746600820","https://openalex.org/W2890324916","https://openalex.org/W2962821226","https://openalex.org/W2963037989","https://openalex.org/W2963087201","https://openalex.org/W2963327228","https://openalex.org/W2963857521","https://openalex.org/W3103836116","https://openalex.org/W4229494842","https://openalex.org/W4239515185"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Convolutional":[1],"Networks":[2],"(DCNs)":[3],"have":[4],"been":[5],"shown":[6],"to":[7,10,16,78,84,93,114,120,156,162,177],"be":[8,175,199],"vulnerable":[9],"adversarial":[11,29,163,193],"examples---perturbed":[12],"inputs":[13],"specifically":[14],"designed":[15],"produce":[17],"intentional":[18],"errors":[19],"in":[20,201],"the":[21,60,87,151,158,188],"learning":[22],"algorithms":[23],"at":[24],"test":[25],"time.":[26],"Existing":[27],"input-agnostic":[28,154],"perturbations":[30,194],"exhibit":[31],"interesting":[32],"visual":[33],"patterns":[34,76],"that":[35,128,171],"are":[36],"currently":[37],"unexplained.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,110],"introduce":[43],"a":[44,80,95,106,142],"structured":[45],"approach":[46,58],"for":[47],"generating":[48],"Universal":[49],"Adversarial":[50],"Perturbations":[51],"(UAPs)":[52],"with":[53,73,99],"procedural":[54,117],"noise":[55,75,90,118],"functions.":[56],"Our":[57],"unveils":[59],"systemic":[61],"vulnerability":[62],"of":[63,86,97,134,153,160,167,179,190],"popular":[64],"DCN":[65,172],"models":[66,161,173],"like":[67],"Inception":[68],"v3":[69],"and":[70,195],"YOLO":[71],"v3,":[72],"single":[74],"able":[77],"fool":[79],"model":[81],"on":[82,145,187],"up":[83],"90%":[85],"dataset.":[88],"Procedural":[89],"allows":[91],"us":[92],"generate":[94],"distribution":[96],"UAPs":[98],"high":[100],"universal":[101,192],"evasion":[102],"rates":[103],"using":[104],"only":[105],"few":[107],"parameters.":[108],"Additionally,":[109],"propose":[111],"Bayesian":[112],"optimization":[113],"efficiently":[115],"learn":[116],"parameters":[119],"construct":[121],"inexpensive":[122],"untargeted":[123],"black-box":[124],"attacks.":[125],"We":[126,148],"demonstrate":[127],"it":[129],"can":[130],"achieve":[131],"an":[132],"average":[133],"less":[135],"than":[136],"10":[137],"queries":[138],"per":[139],"successful":[140],"attack,":[141],"100-fold":[143],"improvement":[144],"existing":[146],"methods.":[147],"further":[149],"motivate":[150],"use":[152],"defences":[155],"increase":[157],"stability":[159],"perturbations.":[164],"The":[165],"universality":[166],"our":[168],"attacks":[169],"suggests":[170],"may":[174],"sensitive":[176],"aggregations":[178],"low-level":[180],"class-agnostic":[181],"features.":[182],"These":[183],"findings":[184],"give":[185],"insight":[186],"nature":[189],"some":[191],"how":[196],"they":[197],"could":[198],"generated":[200],"other":[202],"applications.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-10-05T00:00:00"}