{"id":"https://openalex.org/W7204759488","doi":"https://doi.org/10.18653/2026.findings-emnlp.1510","title":"LongPIBench: A Long-Context Benchmark for Prompt Injection","display_name":"LongPIBench: A Long-Context Benchmark for Prompt Injection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204759488","doi":"https://doi.org/10.18653/2026.findings-emnlp.1510"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1510","doi":"https://doi.org/10.18653/2026.findings-emnlp.1510","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1510","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1510.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.1510.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033795192","display_name":"Yupei Liu","orcid":"https://orcid.org/0000-0003-4300-758X","observed_orcids":["https://orcid.org/0000-0003-4300-758X"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yupei Liu","raw_affiliation_strings":["The Pennsylvania State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University ,","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263654","display_name":"Yuqi Jia","orcid":"https://orcid.org/0009-0006-2954-3609","observed_orcids":["https://orcid.org/0009-0006-2954-3609"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqi Jia","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009102659","display_name":"Neil Zhenqiang Gong","orcid":"https://orcid.org/0000-0002-9900-9309","observed_orcids":["https://orcid.org/0000-0002-9900-9309"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Zhenqiang Gong","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132685319","display_name":"Jinyuan Jia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyuan Jia","raw_affiliation_strings":["The Pennsylvania State University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University ,","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68867335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32132","last_page":"32149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9994999766349792,"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/T11424","display_name":"Security and Verification in Computing","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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":0.9480000138282776},{"id":"https://openalex.org/keywords/prompt-injection-defense","display_name":"prompt injection defense","score":0.7419999837875366},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.35199999809265137},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.75},{"id":"https://openalex.org/keywords/synthetic-dataset","display_name":"synthetic dataset","score":0.4819999933242798},{"id":"https://openalex.org/keywords/defense-evaluation","display_name":"defense evaluation","score":0.5839999914169312},{"id":"https://openalex.org/keywords/resume-screening","display_name":"resume screening","score":0.9610000252723694},{"id":"https://openalex.org/keywords/code-review","display_name":"code review","score":0.996999979019165},{"id":"https://openalex.org/keywords/email-summarization","display_name":"email summarization","score":0.8529999852180481}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.816100001335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901000142097473},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43650001287460327},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703999876976013}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1510","doi":"https://doi.org/10.18653/2026.findings-emnlp.1510","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1510","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1510.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:2608.28411","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28411","pdf_url":"https://arxiv.org/pdf/2608.28411","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28411","doi":"https://doi.org/10.48550/arxiv.2608.28411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28411","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.1510","doi":"https://doi.org/10.18653/2026.findings-emnlp.1510","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1510","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1510.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":[],"sustainable_development_goals_aurora":[{"score":0.4607235789299011,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2495321039","display_name":"Collaborative Research: SaTC: CORE: Medium: Securing LLMs against Prompt Injection Attacks","funder_award_id":"2450937","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G342852933","display_name":"CICI: UCSS: Secure Machine Learning as a Service for Collaborative Scientific Research","funder_award_id":"2530786","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G652313190","display_name":"Collaborative Research: SaTC: CORE: Small: Securing Recommender Systems against Data Poisoning Attacks","funder_award_id":"2125977","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6561886486","display_name":"Collaborative Research: SaTC: EDU: A Lab-based Curriculum for Watermarking AI-Generated Content: Theory, Algorithms, and Robustness Testing","funder_award_id":"2414406","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G777550411","display_name":"Collaborative Research: SaTC: CORE: Medium: Towards Secure Federated Learning","funder_award_id":"2131859","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8377316191","display_name":"AI Institute for Edge Computing Leveraging Next Generation Networks (Athena)","funder_award_id":"2112562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8991437584","display_name":"Collaborative Research: SaTC: CORE: Medium: Securing LLMs against Prompt Injection Attacks","funder_award_id":"2450935","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204759488.pdf","grobid_xml":"https://content.openalex.org/works/W7204759488.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416339344","https://openalex.org/W4417300637","https://openalex.org/W4415314618","https://openalex.org/W7151294679","https://openalex.org/W7147211113","https://openalex.org/W7130424798","https://openalex.org/W7165736730","https://openalex.org/W4414581173","https://openalex.org/W4412889730","https://openalex.org/W4404342689"],"abstract_inverted_index":{"Prompt":[0,197],"injection":[1,17,60,108,117,140],"attacks":[2,26,118],"pose":[3],"a":[4,37,55,80,84,133],"serious":[5],"security":[6],"risk":[7],"to":[8,36,93],"large":[9],"language":[10],"models":[11],"in":[12,29,142],"real-world":[13,85],"applications.However,":[14],"existing":[15],"prompt":[16,59,107,116,139],"benchmarks":[18],"primarily":[19],"focus":[20],"on":[21,101],"short-context":[22],"inputs,":[23],"leaving":[24],"the":[25,41,50],"and":[27,73,83,123,147],"defenses":[28,109,141],"longcontext":[30],"settings":[31],"largely":[32],"unexplored.This":[33],"gap":[34,51],"leads":[35],"substantial":[38],"overestimation":[39],"of":[40,43,95,97,106],"effectiveness":[42],"current":[44],"defenses.In":[45],"this":[46],"paper,":[47],"we":[48,78],"bridge":[49],"by":[52],"introducing":[53],"Long-PIBench,":[54],"long-context":[56,111,144],"benchmark":[57,135],"for":[58,136],"covering":[61],"4":[62],"realistic":[63,143],"application":[64],"scenarios:":[65],"paper":[66],"peer":[67],"review,":[68,72],"resume":[69],"screening,":[70],"code":[71,146],"email":[74],"summary.For":[75],"each":[76],"scenario,":[77],"construct":[79],"synthetic":[81],"dataset":[82],"dataset,":[86],"with":[87],"context":[88],"lengths":[89],"ranging":[90],"from":[91],"thousands":[92,96],"tens":[94],"tokens.The":[98],"evaluation":[99],"results":[100],"LongPIBench":[102],"reveal":[103],"significant":[104],"vulnerabilities":[105],"under":[110],"settings:":[112],"even":[113],"simple":[114],"heuristic":[115],"achieve":[119],"high":[120],"success":[121],"rates":[122],"frequently":[124],"bypass":[125],"state-of-the-art":[126],"defenses.We":[127],"hope":[128],"Long-PIBench":[129],"can":[130],"serve":[131],"as":[132],"practical":[134],"systematically":[137],"evaluating":[138],"scenarios.Our":[145],"data":[148],"are":[149],"available":[150],"at:":[151],"https:":[152],"//github.com/liu00222/LongPIBench.":[153],"Four":[154],"Test":[155],"Scenarios":[156],"Eight":[157,159,163],"Datasets":[158],"Large":[160],"Language":[161],"Models":[162],"Attacks":[164],"Nine":[165],"Detection":[166],"Methods":[167,170],"Six":[168],"Prevention":[169],"Paper":[171],"review":[172,176],"Resume":[173],"screening":[174],"Code":[175],"Email":[177],"summary":[178],"Synthetic":[179],"datasets":[180,182],"Real-world":[181],"Llama-3.1-8B-InstructApertus-8B-Instruct":[183],"\u2022\u2022\u2022\u2022\u2022\u2022":[184,190,196,203],"GPT-4.1":[185],"Na\u00efve":[186],"attack":[187],"Escape":[188],"character":[189],"Authority":[191],"spoof":[192],"Attention":[193],"tracker":[194],"DataSentinel":[195],"guard":[198],"2":[199],"Instructional":[200],"prevention":[201],"Delimiters":[202],"MetaSecAlign":[204]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-09-01T00:00:00"}