{"id":"https://openalex.org/W2942091739","doi":"https://doi.org/10.1109/access.2019.2909068","title":"BadNets: Evaluating Backdooring Attacks on Deep Neural Networks","display_name":"BadNets: Evaluating Backdooring Attacks on Deep Neural Networks","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2942091739","doi":"https://doi.org/10.1109/access.2019.2909068","mag":"2942091739"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2909068","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2909068","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08685687.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08685687.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025675252","display_name":"Tianyu Gu","orcid":"https://orcid.org/0000-0001-5134-3896"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianyu Gu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389879","display_name":"Kang Liu","orcid":"https://orcid.org/0000-0001-7231-8315"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060815601","display_name":"Brendan Dolan-Gavitt","orcid":"https://orcid.org/0000-0002-8867-4282"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Dolan-Gavitt","raw_affiliation_strings":["Department of Computer Science and Engineering, New York University, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010950688","display_name":"Siddharth Garg","orcid":"https://orcid.org/0000-0002-6158-9512"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Garg","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University, New York City, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025675252"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":49.4213,"has_fulltext":true,"cited_by_count":1102,"citation_normalized_percentile":{"value":0.99866662,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"47230","last_page":"47244"},"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":0.9994000196456909,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/backdoor","display_name":"Backdoor","score":0.8847577571868896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8831130266189575},{"id":"https://openalex.org/keywords/traffic-sign-recognition","display_name":"Traffic sign recognition","score":0.6575270295143127},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.6388816833496094},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6379643678665161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6106010675430298},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5981253981590271},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5585722923278809},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5437655448913574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5206415057182312},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4353329539299011},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.29805582761764526},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.2840037941932678},{"id":"https://openalex.org/keywords/traffic-sign","display_name":"Traffic sign","score":0.25673699378967285}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.8847577571868896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8831130266189575},{"id":"https://openalex.org/C6528762","wikidata":"https://www.wikidata.org/wiki/Q1574298","display_name":"Traffic sign recognition","level":4,"score":0.6575270295143127},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6388816833496094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6379643678665161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6106010675430298},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5981253981590271},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5585722923278809},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5437655448913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5206415057182312},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4353329539299011},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29805582761764526},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.2840037941932678},{"id":"https://openalex.org/C2983860417","wikidata":"https://www.wikidata.org/wiki/Q170285","display_name":"Traffic sign","level":3,"score":0.25673699378967285},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2909068","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2909068","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08685687.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3d4eb178da16480f9d549f2e4556e3f7","is_oa":true,"landing_page_url":"https://doaj.org/article/3d4eb178da16480f9d549f2e4556e3f7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 47230-47244 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2909068","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2909068","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08685687.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3480130277","display_name":null,"funder_award_id":"1801495","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2942091739.pdf","grobid_xml":"https://content.openalex.org/works/W2942091739.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W3805906","https://openalex.org/W22861983","https://openalex.org/W34239198","https://openalex.org/W73527130","https://openalex.org/W1552056088","https://openalex.org/W1562491895","https://openalex.org/W1562955078","https://openalex.org/W1599976521","https://openalex.org/W1673923490","https://openalex.org/W1686810756","https://openalex.org/W1945616565","https://openalex.org/W1973813615","https://openalex.org/W1979596264","https://openalex.org/W2062118960","https://openalex.org/W2076063813","https://openalex.org/W2095577883","https://openalex.org/W2112507308","https://openalex.org/W2114016378","https://openalex.org/W2119112357","https://openalex.org/W2128865943","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2151298633","https://openalex.org/W2163605009","https://openalex.org/W2165698076","https://openalex.org/W2183341477","https://openalex.org/W2257979135","https://openalex.org/W2293768274","https://openalex.org/W2296452361","https://openalex.org/W2543927648","https://openalex.org/W2559840118","https://openalex.org/W2603766943","https://openalex.org/W2748789698","https://openalex.org/W2753783305","https://openalex.org/W2759471388","https://openalex.org/W2769986739","https://openalex.org/W2774423163","https://openalex.org/W2807363941","https://openalex.org/W2897865027","https://openalex.org/W2898759955","https://openalex.org/W2934843808","https://openalex.org/W2953106684","https://openalex.org/W2964043980","https://openalex.org/W4232404619","https://openalex.org/W4294375521","https://openalex.org/W4298857966","https://openalex.org/W4299518610","https://openalex.org/W6600171677","https://openalex.org/W6600949241","https://openalex.org/W6601402213","https://openalex.org/W6603010935","https://openalex.org/W6608025168","https://openalex.org/W6620707391","https://openalex.org/W6633682082","https://openalex.org/W6676935882","https://openalex.org/W6682132143","https://openalex.org/W6682778277","https://openalex.org/W6684191040","https://openalex.org/W6686164453","https://openalex.org/W6736092963","https://openalex.org/W6743581629","https://openalex.org/W6756333562"],"related_works":["https://openalex.org/W4320031223","https://openalex.org/W3015678314","https://openalex.org/W4281902577","https://openalex.org/W4328053081","https://openalex.org/W4366850823","https://openalex.org/W3086120435","https://openalex.org/W4385573555","https://openalex.org/W4281570223","https://openalex.org/W4388858813","https://openalex.org/W3210342734"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"techniques":[2,227],"have":[3,237],"achieved":[4],"state-of-the-art":[5,88],"performance":[6,89],"on":[7,29,46,90,100,190],"a":[8,33,54,74,83,112,117,127,133,146,183],"wide":[9],"variety":[10],"of":[11,27,109,188,212],"recognition":[12],"and":[13,94,181,230,242],"classification":[14],"tasks.":[15],"However,":[16],"these":[17],"networks":[18,205,214],"are":[19,50,206],"typically":[20],"computationally":[21],"expensive":[22],"to":[23,41,151,217],"train,":[24],"requiring":[25],"weeks":[26],"computation":[28],"many":[30,35],"GPUs;":[31],"as":[32,142,235],"result,":[34],"users":[36],"outsource":[37],"the":[38,42,63,87,91,107,152,161,173,193,210],"training":[39,65,93],"procedure":[40],"cloud":[43],"or":[44,82],"rely":[45],"pre-trained":[47],"models":[48],"that":[49,62,85,138,160,201],"then":[51,156],"fine-tuned":[52],"for":[53,178,223,228,240],"specific":[55,101],"task.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,123,155,236],"show":[61,157],"outsourced":[64],"introduces":[66],"new":[67],"security":[68],"risks:":[69],"an":[70,186],"adversary":[71],"can":[72,169],"create":[73],"maliciously":[75],"trained":[76],"network":[77,174],"(a":[78],"backdoored":[79,118],"neural":[80,204,213,232],"network,":[81],"BadNet)":[84],"has":[86],"user's":[92],"validation":[95],"samples":[96],"but":[97],"behaves":[98],"badly":[99],"attacker-chosen":[102],"inputs.":[103],"We":[104],"first":[105],"explore":[106],"properties":[108],"BadNets":[110],"in":[111,126,158,163,185,203],"toy":[113],"example,":[114],"by":[115,131],"creating":[116,132],"handwritten":[119],"digit":[120],"classifier.":[121],"Next,":[122],"demonstrate":[124,200],"backdoors":[125,202],"more":[128],"realistic":[129],"scenario":[130],"U.S.":[134,165],"street":[135,166],"sign":[136,167],"classifier":[137],"identifies":[139],"stop":[140,153],"signs":[141],"speed":[143],"limits":[144],"when":[145,192],"special":[147],"sticker":[148],"is":[149,175,196,215],"added":[150],"sign;":[154],"addition":[159],"backdoor":[162,194],"our":[164],"detector":[168],"persist":[170],"even":[171],"if":[172],"later":[176],"retrained":[177],"another":[179],"task":[180],"cause":[182],"drop":[184],"accuracy":[187],"25%":[189],"average":[191],"trigger":[195],"present.":[197],"These":[198],"results":[199],"both":[207],"powerful":[208],"and-because":[209],"behavior":[211],"difficult":[216],"explicate-stealthy.":[218],"This":[219],"paper":[220],"provides":[221],"motivation":[222],"further":[224],"research":[225],"into":[226],"verifying":[229,241],"inspecting":[231],"networks,":[233],"just":[234],"developed":[238],"tools":[239],"debugging":[243],"software.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":47},{"year":2025,"cited_by_count":272},{"year":2024,"cited_by_count":245},{"year":2023,"cited_by_count":196},{"year":2022,"cited_by_count":138},{"year":2021,"cited_by_count":117},{"year":2020,"cited_by_count":68},{"year":2019,"cited_by_count":19}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}