{"id":"https://openalex.org/W7202210666","doi":"https://doi.org/10.48550/arxiv.2608.07636","title":"Adversarial Attacks on Deep OCR Systems","display_name":"Adversarial Attacks on Deep OCR Systems","publication_year":2026,"publication_date":"2026-08-07","ids":{"openalex":"https://openalex.org/W7202210666","doi":"https://doi.org/10.48550/arxiv.2608.07636"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.07636","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07636","pdf_url":"https://arxiv.org/pdf/2608.07636","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.07636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148866350","display_name":"Wenbo Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Wenbo","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081924890","display_name":"Hongzong Li","orcid":"https://orcid.org/0000-0002-5774-7557","observed_orcids":["https://orcid.org/0000-0002-5774-7557","https://orcid.org/0009-0007-7857-1689"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LI, Hongzong","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134912108","display_name":"Yanyun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wang, Yanyun","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146444956","display_name":"Jiahao MA","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"MA, Jiahao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069120843","display_name":"Shuxin Zhuang","orcid":"https://orcid.org/0000-0002-8782-7996","observed_orcids":["https://orcid.org/0000-0002-8782-7996"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhuang, Shuxin","raw_affiliation_strings":["Centre for Artificial Intelligence and Robotics , Chinese Academy of Sciences","City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence and Robotics , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125031925","display_name":"Rong Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Feng, Rong","raw_affiliation_strings":["Centre for Artificial Intelligence and Robotics , Chinese Academy of Sciences","City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence and Robotics , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146547578","display_name":"Shiqin Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Shiqin","raw_affiliation_strings":["Centre for Artificial Intelligence and Robotics , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence and Robotics , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146462754","display_name":"Zi Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liang, Zi","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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":0.9990000128746033,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0003000000142492354,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":9.999999747378752e-05,"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-attacks","display_name":"adversarial attacks","score":0.9779999852180481},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.722000002861023},{"id":"https://openalex.org/keywords/black-box-attacks","display_name":"black-box attacks","score":0.7059999704360962},{"id":"https://openalex.org/keywords/derivative-free-optimization","display_name":"derivative-free optimization","score":0.8769999742507935},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7699999809265137},{"id":"https://openalex.org/keywords/targeted-attacks","display_name":"targeted attacks","score":0.39899998903274536},{"id":"https://openalex.org/keywords/untargeted-attacks","display_name":"untargeted attacks","score":0.9449999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713699996471405},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6693999767303467},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.07636","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07636","pdf_url":"https://arxiv.org/pdf/2608.07636","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.2608.07636","doi":"https://doi.org/10.48550/arxiv.2608.07636","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.07636","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:2608.07636","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07636","pdf_url":"https://arxiv.org/pdf/2608.07636","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202210666.pdf","grobid_xml":"https://content.openalex.org/works/W7202210666.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2503523779","https://openalex.org/W2640329709","https://openalex.org/W2736899637","https://openalex.org/W2765384636","https://openalex.org/W2773022113","https://openalex.org/W2785681938","https://openalex.org/W2786104118","https://openalex.org/W2787708942","https://openalex.org/W2951807304","https://openalex.org/W3004923694","https://openalex.org/W3015625436","https://openalex.org/W4294517337","https://openalex.org/W4312233877","https://openalex.org/W4327810158","https://openalex.org/W4382202677","https://openalex.org/W4386228584","https://openalex.org/W4386437528","https://openalex.org/W4386596887","https://openalex.org/W4393157467","https://openalex.org/W4402713111","https://openalex.org/W4402955109","https://openalex.org/W4407794264","https://openalex.org/W4416055645","https://openalex.org/W7133239785"],"related_works":["https://openalex.org/W2785681938","https://openalex.org/W3111874935","https://openalex.org/W4387635507","https://openalex.org/W3004923694","https://openalex.org/W4316830043","https://openalex.org/W4413823380","https://openalex.org/W4381329083","https://openalex.org/W7203889917","https://openalex.org/W4416851502","https://openalex.org/W7171435229"],"abstract_inverted_index":{"Deep-OCR":[0,131],"(DeepSeek-OCR)":[1],"advances":[2],"document":[3],"recognition":[4],"by":[5,81],"treating":[6],"the":[7,37,42,56,73,89,97,110,133,170],"visual":[8],"modality":[9],"as":[10,75],"an":[11],"optical":[12],"compression":[13],"medium,":[14],"enabling":[15],"long-context":[16],"OCR":[17,51],"at":[18],"low":[19],"token":[20],"cost.":[21],"However,":[22],"its":[23],"increased":[24],"complexity":[25],"may":[26],"introduce":[27],"new":[28],"security":[29],"vulnerabilities.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,164],"present,":[35],"to":[36],"best":[38],"of":[39,109],"our":[40],"knowledge,":[41],"first":[43],"pure":[44],"black-box":[45],"adversarial":[46],"attack":[47,74,135],"against":[48],"a":[49,76,82,100],"generative":[50],"vision-language":[52],"model,":[53],"where":[54],"only":[55],"decoded":[57],"string":[58,90],"can":[59],"be":[60],"queried":[61],"and":[62,95,125,136,139,148],"no":[63],"gradients,":[64],"logits,":[65],"or":[66],"model":[67],"internals":[68],"are":[69],"available.":[70],"We":[71],"recast":[72],"zeroth-order":[77],"optimization":[78],"problem":[79],"driven":[80],"bounded":[83],"scalar":[84],"loss":[85],"defined":[86],"directly":[87],"on":[88,130],"output":[91],"via":[92],"sequence":[93],"similarity,":[94],"estimate":[96],"gradient":[98],"with":[99,116],"random-direction":[101],"finite-difference":[102],"scheme":[103],"whose":[104],"query":[105],"cost":[106],"is":[107,173],"independent":[108],"image":[111],"dimension.":[112],"An":[113],"Adam":[114],"update":[115],"ell_infinity":[117],"projection":[118],"yields":[119],"imperceptible":[120],"perturbations":[121],"for":[122],"both":[123],"untargeted":[124,162],"targeted":[126,156,167],"objectives.":[127],"Pilot":[128],"experiments":[129],"validate":[132],"string-only":[134],"evaluation":[137,172],"pipeline":[138],"expose":[140],"severe":[141],"qualitative":[142],"decoder":[143],"failures,":[144],"including":[145],"repetition,":[146],"truncation,":[147],"prompt":[149],"leakage.":[150],"They":[151],"also":[152],"show":[153],"that":[154],"controlled":[155],"rewriting":[157],"remains":[158],"substantially":[159],"harder":[160],"than":[161],"degradation;":[163],"avoid":[165],"claiming":[166],"success":[168],"until":[169],"pre-registered":[171],"complete.":[174]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-12T00:00:00"}