{"id":"https://openalex.org/W4400222605","doi":"https://doi.org/10.1109/wacv61042.2026.00075","title":"Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness","display_name":"Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4400222605","doi":"https://doi.org/10.1109/wacv61042.2026.00075"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.19622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009422392","display_name":"Erh\u2013Chung Chen","orcid":"https://orcid.org/0000-0003-1780-8383"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Erh-Chung Chen","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108479300","display_name":"I\u2010Hsin Chung","orcid":"https://orcid.org/0000-0003-4555-9257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I-Hsin Chung","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058589126","display_name":"Che\u2013Rung Lee","orcid":"https://orcid.org/0000-0003-3940-4478"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Rung Lee","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00213094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"698","last_page":"707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9986000061035156,"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":0.9986000061035156,"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/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.957099974155426,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8134316802024841},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.766994833946228},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7438763380050659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5412606000900269},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39392995834350586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2828790545463562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27729350328445435}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8134316802024841},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.766994833946228},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7438763380050659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5412606000900269},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39392995834350586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2828790545463562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27729350328445435},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.19622","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19622","pdf_url":"https://arxiv.org/pdf/2406.19622","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,"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.2406.19622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.19622","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.19622","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19622","pdf_url":"https://arxiv.org/pdf/2406.19622","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,"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":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400222605.pdf","grobid_xml":"https://content.openalex.org/works/W4400222605.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119"],"abstract_inverted_index":{"As":[0],"deep":[1],"neural":[2,156],"networks":[3],"(DNNs)":[4],"are":[5],"increasingly":[6],"deployed":[7],"in":[8,39],"sensitive":[9],"applications,":[10],"ensuring":[11],"their":[12,63],"security":[13],"and":[14,65,124],"robustness":[15,43,83,127],"has":[16],"become":[17],"critical.":[18],"A":[19],"major":[20],"threat":[21],"to":[22,34,85],"DNNs":[23],"arises":[24],"from":[25,48],"adversarial":[26,40,94,121,170],"attacks,":[27],"where":[28],"small":[29],"input":[30],"perturbations":[31],"can":[32,116],"lead":[33],"incorrect":[35],"predictions.":[36],"Recent":[37],"advances":[38],"training":[41,122],"improve":[42],"by":[44],"incorporating":[45],"additional":[46],"examples":[47],"external":[49],"datasets":[50],"or":[51,149],"generative":[52,133],"models.":[53],"However,":[54],"these":[55],"methods":[56],"often":[57],"incur":[58],"high":[59],"computational":[60,144],"costs,":[61],"limiting":[62],"practicality":[64],"hindering":[66],"real-world":[67],"deployment.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"a":[74,100,161],"cost-efficient":[75],"alternative":[76],"based":[77],"on":[78],"Lipschitz":[79],"continuity":[80],"that":[81,138],"achieves":[82],"comparable":[84],"models":[86,129],"trained":[87],"with":[88,119],"extensive":[89],"supplementary":[90],"data.":[91,134],"Unlike":[92],"conventional":[93],"training,":[95],"our":[96,114,139],"method":[97,115],"requires":[98],"only":[99,142],"single":[101],"pass":[102],"over":[103],"the":[104,126,151],"dataset":[105],"without":[106,130],"gradient":[107],"estimation,":[108],"making":[109],"it":[110],"highly":[111],"efficient.":[112],"Furthermore,":[113],"integrate":[117],"seamlessly":[118],"existing":[120],"frameworks":[123],"enhances":[125],"of":[128,154],"requiring":[131],"extra":[132],"Experimental":[135],"results":[136],"show":[137],"approach":[140],"not":[141],"reduces":[143],"overhead":[145],"but":[146],"also":[147],"maintains":[148],"improves":[150],"defensive":[152],"capabilities":[153],"robust":[155],"networks.":[157],"This":[158],"work":[159],"opens":[160],"promising":[162],"direction":[163],"for":[164],"developing":[165],"practical,":[166],"scalable":[167],"defenses":[168],"against":[169],"attacks.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-07-02T00:00:00"}