{"id":"https://openalex.org/W4386147982","doi":"https://doi.org/10.1145/3581783.3612032","title":"PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification","display_name":"PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4386147982","doi":"https://doi.org/10.1145/3581783.3612032"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612032","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068863636","display_name":"Yizhen Yuan","orcid":"https://orcid.org/0009-0002-3714-8044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yizhen Yuan","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585460","display_name":"Rui Kong","orcid":"https://orcid.org/0009-0003-2889-2266"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Kong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103141427","display_name":"Shenghao Xie","orcid":"https://orcid.org/0009-0003-1024-1166"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghao Xie","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628298","display_name":"Yuanchun Li","orcid":"https://orcid.org/0000-0002-1591-2526"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchun Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University & Shanghai AI Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University & Shanghai AI Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102880548","display_name":"Yunxin Liu","orcid":"https://orcid.org/0000-0001-7352-8955"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxin Liu","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University & Shanghai AI Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University & Shanghai AI Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068863636"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2075,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83306854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9134","last_page":"9142"},"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":0.963100016117096,"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":0.9607999920845032,"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":0.9993394017219543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7809256315231323},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6101815104484558},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5895546078681946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5658016204833984},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3643028140068054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34839439392089844}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9993394017219543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809256315231323},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6101815104484558},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5895546078681946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5658016204833984},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3643028140068054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34839439392089844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612032","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.11822","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.11822","pdf_url":"https://arxiv.org/pdf/2308.11822","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"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612032","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4968693648","display_name":null,"funder_award_id":"62272261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386147982.pdf","grobid_xml":"https://content.openalex.org/works/W4386147982.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2145287260","https://openalex.org/W2155904486","https://openalex.org/W2525305541","https://openalex.org/W2765424254","https://openalex.org/W2798302089","https://openalex.org/W2902867332","https://openalex.org/W2905423756","https://openalex.org/W2934843808","https://openalex.org/W2951727855","https://openalex.org/W2963163009","https://openalex.org/W2963302614","https://openalex.org/W2979495046","https://openalex.org/W3006436762","https://openalex.org/W3025573667","https://openalex.org/W3083045783","https://openalex.org/W3098350627","https://openalex.org/W3102651566","https://openalex.org/W3103557498","https://openalex.org/W3111943226","https://openalex.org/W3119652083","https://openalex.org/W3121099749","https://openalex.org/W3128390792","https://openalex.org/W3163168187","https://openalex.org/W3210227505","https://openalex.org/W3214636874","https://openalex.org/W4214564822","https://openalex.org/W4299301436","https://openalex.org/W4304099366","https://openalex.org/W4319301003","https://openalex.org/W6717243457"],"related_works":["https://openalex.org/W4320031223","https://openalex.org/W4200629851","https://openalex.org/W4281902577","https://openalex.org/W4309417370","https://openalex.org/W4292107232","https://openalex.org/W3009072493","https://openalex.org/W4386080799","https://openalex.org/W3140988292","https://openalex.org/W4401407399","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Backdoor":[0],"attack":[1,55,191,212],"is":[2,108,213],"a":[3,48,96,158],"major":[4],"threat":[5],"to":[6,15,30,47,94,123,152,163,181,196],"deep":[7,183],"learning":[8,184],"systems":[9],"in":[10,102,170,205],"safety-critical":[11],"scenarios,":[12],"which":[13,45,107],"aims":[14],"trigger":[16,142],"misbehavior":[17],"of":[18,81,104,128,167,194],"neural":[19,33],"network":[20,34],"models":[21,35,185],"under":[22],"attacker-controlled":[23,141],"conditions.":[24],"However,":[25],"most":[26,127],"backdoor":[27,54,71,83,100,155],"attacks":[28,72],"have":[29],"modify":[31],"the":[32,63,86,90,105,111,115,129,136,154,165,168,211],"through":[36],"training":[37,87,150],"with":[38,114,189],"poisoned":[39],"data":[40,88],"and/or":[41],"direct":[42],"model":[43,78,112],"editing,":[44],"leads":[46],"common":[49,182],"but":[50],"false":[51],"belief":[52],"that":[53,70,176,210],"can":[56,73,120,178],"be":[57,74,121,179],"easily":[58],"avoided":[59],"by":[60],"properly":[61],"protecting":[62],"model.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,92,202],"show":[69,175,209],"achieved":[75],"without":[76],"any":[77],"modification.":[79],"Instead":[80],"injecting":[82],"logic":[84],"into":[85,110],"or":[89],"model,":[91],"propose":[93],"place":[95],"carefully-designed":[97],"patch":[98,119,156,169],"(namely":[99],"patch)":[101],"front":[103],"camera,":[106],"fed":[109],"together":[113],"input":[116,137],"images.":[117],"The":[118],"trained":[122],"behave":[124],"normally":[125],"at":[126],"time,":[130],"while":[131],"producing":[132],"wrong":[133],"prediction":[134],"when":[135],"image":[138],"contains":[139],"an":[140,148,190],"object.":[143],"Our":[144],"main":[145],"techniques":[146],"include":[147],"effective":[149],"method":[151,162],"generate":[153],"and":[157,208],"digital-physical":[159],"transformation":[160],"modeling":[161],"enhance":[164],"feasibility":[166],"real":[171],"deployments.":[172],"Extensive":[173],"experiments":[174],"PatchBackdoor":[177,204],"applied":[180],"(VGG,":[186],"MobileNet,":[187],"ResNet)":[188],"success":[192],"rate":[193],"93%":[195],"99%":[197],"on":[198],"classification":[199],"tasks.":[200],"Moreover,":[201],"implement":[203],"real-world":[206],"scenarios":[207],"still":[214],"threatening.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}