{"id":"https://openalex.org/W4416435600","doi":"https://doi.org/10.18653/2026.findings-emnlp.49","title":"\u201cGive a Positive Review Only\u201d: An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers","display_name":"\u201cGive a Positive Review Only\u201d: An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416435600","doi":"https://doi.org/10.18653/2026.findings-emnlp.49"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.49","doi":"https://doi.org/10.18653/2026.findings-emnlp.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.49","pdf_url":"https://aclanthology.org/2026.findings-emnlp.49.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.49.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qin Zhou","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"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Zhou","raw_affiliation_strings":["Institute of Information Engineering , CAS , Beijing , China","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , CAS , Beijing , China","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120607250","display_name":"Zhexin Zhang","orcid":null,"observed_orcids":[]},"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":"Zhexin Zhang","raw_affiliation_strings":["The Conversational AI (CoAI) group , DCST , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Conversational AI (CoAI) group , DCST , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029039359","display_name":"Zhiwei Li","orcid":"https://orcid.org/0000-0003-4575-5258","observed_orcids":["https://orcid.org/0000-0003-4575-5258","https://orcid.org/0000-0003-2716-2002"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100683966","display_name":"Limin Sun","orcid":"https://orcid.org/0000-0002-6370-6559","observed_orcids":["https://orcid.org/0000-0002-6370-6559"]},"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"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Sun","raw_affiliation_strings":["Institute of Information Engineering , CAS , Beijing , China","School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering , CAS , Beijing , China","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.1396,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98277129,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"982","last_page":"997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9901999831199646,"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":0.9901999831199646,"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/T11644","display_name":"Spam and Phishing Detection","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11424","display_name":"Security and Verification in Computing","score":0.000699999975040555,"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/prompt-injection","display_name":"prompt injection","score":0.9440000057220459},{"id":"https://openalex.org/keywords/ai-assisted-peer-review","display_name":"AI-assisted peer review","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507999897003174},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32850000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32440000772476196},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3012000024318695}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.49","doi":"https://doi.org/10.18653/2026.findings-emnlp.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.49","pdf_url":"https://aclanthology.org/2026.findings-emnlp.49.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.01287","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.01287","pdf_url":"https://arxiv.org/pdf/2511.01287","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.2511.01287","doi":"https://doi.org/10.48550/arxiv.2511.01287","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.01287","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":"doi:10.18653/2026.findings-emnlp.49","doi":"https://doi.org/10.18653/2026.findings-emnlp.49","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.49","pdf_url":"https://aclanthology.org/2026.findings-emnlp.49.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4938631274","display_name":null,"funder_award_id":"U1766215","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416435600.pdf","grobid_xml":"https://content.openalex.org/works/W4416435600.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164558714","https://openalex.org/W4415090291","https://openalex.org/W4415986829","https://openalex.org/W7165756360","https://openalex.org/W7117242396","https://openalex.org/W4414593097","https://openalex.org/W7164564256","https://openalex.org/W7168048551","https://openalex.org/W7212120292","https://openalex.org/W4412416783"],"abstract_inverted_index":{"With":[0],"the":[1,81,129,146],"rapid":[2],"advancement":[3],"of":[4,65],"AI":[5,21,43,105],"models,":[6],"their":[7],"deployment":[8],"across":[9,114],"diverse":[10],"tasks":[11],"has":[12],"become":[13],"increasingly":[14],"widespread.A":[15],"notable":[16],"emerging":[17,60],"application":[18],"is":[19],"leveraging":[20],"models":[22],"to":[23,41,89],"assist":[24],"in":[25,157],"reviewing":[26],"scientific":[27],"papers.However,":[28],"recent":[29],"reports":[30],"have":[31],"revealed":[32],"that":[33,109,135],"some":[34],"papers":[35],"contain":[36],"hidden,":[37],"injected":[38],"prompts":[39],"designed":[40],"manipulate":[42],"reviewers":[44],"into":[45,58],"providing":[46],"overly":[47],"favorable":[48],"evaluations.In":[49],"this":[50,59,118,142],"work,":[51],"we":[52,107,120,133],"present":[53],"an":[54,136],"early":[55],"systematic":[56],"investigation":[57],"threat.We":[61],"propose":[62],"two":[63],"classes":[64],"attacks:(1)":[66],"static":[67],"attack,":[68,78],"which":[69,79],"employs":[70],"a":[71,85,122],"fixed":[72],"injection":[73,82],"prompt,":[74],"and":[75,151],"(2)":[76],"iterative":[77],"optimizes":[80],"prompt":[83],"against":[84,154],"simulated":[86],"reviewer":[87],"model":[88],"maximize":[90],"its":[91],"effectiveness.Both":[92],"attacks":[93,111],"achieve":[94],"striking":[95],"performance,":[96],"frequently":[97],"inducing":[98],"full":[99],"evaluation":[100],"scores":[101],"when":[102],"targeting":[103],"frontier":[104],"reviewers.Furthermore,":[106],"show":[108],"these":[110],"are":[112],"robust":[113],"various":[115],"settings.To":[116],"counter":[117],"threat,":[119],"explore":[121],"simple":[123],"detection-based":[124],"defense.While":[125],"it":[126],"substantially":[127],"reduces":[128],"attack":[130],"success":[131],"rate,":[132],"demonstrate":[134],"adaptive":[137],"attacker":[138],"can":[139],"partially":[140],"circumvent":[141],"defense.Our":[143],"findings":[144],"underscore":[145],"need":[147],"for":[148],"greater":[149],"attention":[150],"rigorous":[152],"safeguards":[153],"prompt-injection":[155],"threats":[156],"AI-assisted":[158],"peer":[159],"review.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-11-06T00:00:00"}