{"id":"https://openalex.org/W2962872506","doi":"https://doi.org/10.1109/cvpr.2019.00059","title":"Feature Denoising for Improving Adversarial Robustness","display_name":"Feature Denoising for Improving Adversarial Robustness","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2962872506","doi":"https://doi.org/10.1109/cvpr.2019.00059","mag":"2962872506"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2019.00059","doi":"https://doi.org/10.1109/cvpr.2019.00059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2019.00059","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.03411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022344556","display_name":"Cihang Xie","orcid":"https://orcid.org/0000-0003-1243-8045","observed_orcids":["https://orcid.org/0000-0003-1243-8045"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cihang Xie","raw_affiliation_strings":["Johns Hopkins Univ","Facebook AI Research","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins Univ","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018369948","display_name":"Yuxin Wu","orcid":"https://orcid.org/0000-0002-7348-6609","observed_orcids":["https://orcid.org/0000-0002-7348-6609"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxin Wu","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109065097","display_name":"Laurens J. P. van der Maaten","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Laurens van der Maaten","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249","observed_orcids":["https://orcid.org/0000-0001-5207-9249"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan L. Yuille","raw_affiliation_strings":["Johns Hopkins Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins Univ","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100700361","display_name":"Kaiming He","orcid":"https://orcid.org/0000-0001-7318-9658","observed_orcids":["https://orcid.org/0000-0001-7318-9658"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiming He","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":43.64,"has_fulltext":true,"cited_by_count":982,"citation_normalized_percentile":{"value":0.99895323,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"509"},"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/T11424","display_name":"Security and Verification in Computing","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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-robustness","display_name":"adversarial robustness","score":0.9909999966621399},{"id":"https://openalex.org/keywords/feature-denoising","display_name":"feature denoising","score":0.9359999895095825},{"id":"https://openalex.org/keywords/adversarial-attacks","display_name":"adversarial attacks","score":0.9010000228881836},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.7839999794960022},{"id":"https://openalex.org/keywords/non-local-means-filter","display_name":"non-local means","score":0.7760000228881836},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7960000038146973},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.8130000233650208},{"id":"https://openalex.org/keywords/black-box-attacks","display_name":"black-box attacks","score":0.8379999995231628},{"id":"https://openalex.org/keywords/white-box-attacks","display_name":"white-box attacks","score":0.9649999737739563},{"id":"https://openalex.org/keywords/pgd-attacks","display_name":"PGD attacks","score":0.7559999823570251}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8981737494468689},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8301846981048584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474390268325806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6473246216773987},{"id":"https://openalex.org/C180932941","wikidata":"https://www.wikidata.org/wiki/Q997233","display_name":"White box","level":2,"score":0.6128748059272766},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5325718522071838},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5179961919784546},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5084806680679321},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4952773153781891},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48818355798721313},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.41984841227531433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4174203872680664},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2019.00059","doi":"https://doi.org/10.1109/cvpr.2019.00059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2019.00059","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.03411","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.03411","pdf_url":"https://arxiv.org/pdf/1812.03411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.1812.03411","doi":"https://doi.org/10.48550/arxiv.1812.03411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.03411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.03411","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.03411","pdf_url":"https://arxiv.org/pdf/1812.03411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962872506.pdf","grobid_xml":"https://content.openalex.org/works/W2962872506.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W1999360130","https://openalex.org/W2097073572","https://openalex.org/W2099244020","https://openalex.org/W2103559027","https://openalex.org/W2117539524","https://openalex.org/W2147800946","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2206858481","https://openalex.org/W2460937040","https://openalex.org/W2549139847","https://openalex.org/W2622263826","https://openalex.org/W2626778328","https://openalex.org/W2640329709","https://openalex.org/W2765384636","https://openalex.org/W2774018344","https://openalex.org/W2774644650","https://openalex.org/W2787708942","https://openalex.org/W2791953061","https://openalex.org/W2795727551","https://openalex.org/W2807108439","https://openalex.org/W2884821828","https://openalex.org/W2897355816","https://openalex.org/W2963091558","https://openalex.org/W2963207607","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W6739622702"],"related_works":["https://openalex.org/W3022223508","https://openalex.org/W3124707345","https://openalex.org/W4385880757","https://openalex.org/W7118093577","https://openalex.org/W4390839235","https://openalex.org/W4313270448","https://openalex.org/W7221506532","https://openalex.org/W4205387611","https://openalex.org/W2789041624","https://openalex.org/W4394627326"],"abstract_inverted_index":{"Adversarial":[0,132],"attacks":[1,101],"to":[2,8,25],"image":[3],"classification":[4,142],"systems":[5],"present":[6],"challenges":[7],"convolutional":[9],"networks":[10,53,68,80],"and":[11,91,134],"opportunities":[12],"for":[13],"understanding":[14],"them.":[15],"This":[16],"study":[17],"suggests":[18],"that":[19,43,56],"adversarial":[20,45,75,86],"perturbations":[21],"on":[22,131,144],"images":[23],"lead":[24],"noise":[26],"in":[27,85,88,129],"the":[28,58,66,83,155],"features":[29,59],"constructed":[30],"by":[31,35,47,158],"these":[32],"networks.":[33],"Motivated":[34],"this":[36],"observation,":[37],"we":[38],"develop":[39],"new":[40],"network":[41],"architectures":[42],"increase":[44],"robustness":[46,87],"performing":[48],"feature":[49,78],"denoising.":[50],"Specifically,":[51],"our":[52,77,108,119],"contain":[54],"blocks":[55],"denoise":[57],"using":[60],"non-local":[61],"means":[62],"or":[63],"other":[64],"filters;":[65],"entire":[67],"are":[69],"trained":[70],"end-to-end.":[71],"When":[72],"combined":[73],"with":[74],"training,":[76],"denoising":[79],"substantially":[81],"improve":[82],"state-of-the-art":[84],"both":[89],"white-box":[90,100,117],"black-box":[92],"attack":[93],"settings.":[94],"On":[95],"ImageNet,":[96],"under":[97,113],"10-iteration":[98],"PGD":[99,116],"where":[102],"prior":[103],"art":[104],"has":[105],"27.9%":[106],"accuracy,":[107],"method":[109,120,125],"achieves":[110],"55.7%;":[111],"even":[112],"extreme":[114],"2000-iteration":[115],"attacks,":[118],"secures":[121],"42.6%":[122],"accuracy.":[123],"Our":[124],"was":[126],"ranked":[127],"first":[128],"Competition":[130],"Attacks":[133],"Defenses":[135],"(CAAD)":[136],"2018":[137],"---":[138],"it":[139],"achieved":[140],"50.6%":[141],"accuracy":[143],"a":[145],"secret,":[146],"ImageNet-like":[147],"test":[148],"dataset":[149],"against":[150],"48":[151],"unknown":[152],"attackers,":[153],"surpassing":[154],"runner-up":[156],"approach":[157],"~10%.":[159],"Code":[160],"is":[161],"available":[162],"at":[163],"https://github.com/facebookresearch/ImageNet-Adversarial-Training.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":64},{"year":2025,"cited_by_count":114},{"year":2024,"cited_by_count":122},{"year":2023,"cited_by_count":141},{"year":2022,"cited_by_count":125},{"year":2021,"cited_by_count":179},{"year":2020,"cited_by_count":161},{"year":2019,"cited_by_count":71},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-07-30T00:00:00"}