{"id":"https://openalex.org/W7164564256","doi":"https://doi.org/10.48550/arxiv.2606.12716","title":"Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review","display_name":"Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164564256","doi":"https://doi.org/10.48550/arxiv.2606.12716"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.12716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12716","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.12716","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138513420","display_name":"Xinyu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138515720","display_name":"Rana Muhammad Shahroz Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Rana Muhammad Shahroz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073136550","display_name":"Zhewei Xu","orcid":"https://orcid.org/0000-0003-4718-6175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138507268","display_name":"Zhen Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050105433","display_name":"T X Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.47850000858306885,"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":0.47850000858306885,"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/T10028","display_name":"Topic Modeling","score":0.1370999962091446,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.05090000107884407,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6388999819755554},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.592199981212616},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47519999742507935},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.43939998745918274},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3312000036239624},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.2946000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485000252723694},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47519999742507935},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226999878883362},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.12716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12716","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.12716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.12716","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,28,133,162],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"and":[7,17,103,139,149,152,173,197],"Multimodal":[8],"LLMs":[9],"(MLLMs)":[10],"into":[11],"scientific":[12,29,127],"peer-review":[13,49,63,106,123],"workflows":[14],"introduces":[15],"novel":[16],"significant":[18,42],"risks":[19],"for":[20,83],"adversarial":[21],"manipulation,":[22],"especially":[23],"given":[24],"the":[25,54,95,159,193],"multimodal":[26,122],"nature":[27],"papers":[30],"where":[31],"figures,":[32],"not":[33],"just":[34],"text,":[35],"convey":[36],"core":[37],"evidence.":[38],"This":[39],"creates":[40],"a":[41,62,68,78,120,130,154],"gap:":[43],"current":[44],"robustness":[45],"studies":[46],"on":[47,116],"AI":[48,186],"are":[50,188],"overwhelmingly":[51],"text-only.":[52],"Moreover,":[53],"problem":[55],"is":[56,114],"distinct":[57],"from":[58],"standard":[59],"jailbreaking,":[60],"as":[61],"attack":[64],"seeks":[65],"to":[66,100,144,170,201],"induce":[67],"domain-specific,":[69,109],"targeted":[70],"failure":[71],"(e.g.,":[72],"\"inflate":[73],"this":[74],"score\")":[75],"rather":[76],"than":[77],"general":[79],"safety":[80],"policy":[81],"violation,":[82],"which":[84],"no":[85],"practical":[86,155],"defenses":[87],"exist.":[88],"To":[89],"address":[90],"this,":[91],"we":[92],"introduce":[93],"PaperGuard,":[94],"first":[96],"comprehensive":[97],"benchmark":[98],"designed":[99,143],"systematically":[101],"evaluate":[102],"defend":[104],"AI-generated":[105],"against":[107],"these":[108],"cross-modal":[110],"attacks.":[111],"Our":[112,177],"framework":[113],"built":[115],"three":[117],"pillars:":[118],"(1)":[119],"new":[121],"dataset":[124],"spanning":[125],"multiple":[126],"domains;":[128],"(2)":[129],"unified":[131],"suite":[132],"attacks,":[134],"including":[135],"black-box":[136],"prompt":[137],"injections":[138],"white-box":[140],"perturbations,":[141],"specifically":[142],"target":[145],"both":[146],"text":[147],"(GCG)":[148],"figures":[150],"(PGD);":[151],"(3)":[153],"defense,":[156],"motivated":[157],"by":[158],"long-context":[160],"challenge":[161],"academic":[163],"papers,":[164],"that":[165,185],"uses":[166],"chunk-based":[167],"embedding":[168],"search":[169],"efficiently":[171],"localize":[172],"mitigate":[174],"harmful":[175],"instructions.":[176],"extensive":[178],"experiments,":[179],"conducted":[180],"across":[181],"state-of-the-art":[182],"models,":[183],"confirm":[184],"reviewers":[187],"pervasively":[189],"vulnerable.":[190],"PaperGuard":[191],"establishes":[192],"foundational":[194],"benchmark,":[195],"protocols,":[196],"actionable":[198],"defense":[199],"necessary":[200],"pioneer":[202],"trustworthy,":[203],"attack-resilient":[204],"AI-assisted":[205],"scholarly":[206],"reviewing.":[207]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-13T00:00:00"}