{"id":"https://openalex.org/W7196941018","doi":"https://doi.org/10.52202/085713-0666","title":"WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks","display_name":"WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7196941018","doi":"https://doi.org/10.52202/085713-0666"},"language":"en","primary_location":{"id":"doi:10.52202/085713-0666","doi":"https://doi.org/10.52202/085713-0666","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0666","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.18575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121333553","display_name":"Ivan Evtimov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Evtimov","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009367143","display_name":"Arman Serikuly Zharmagambetov","orcid":"https://orcid.org/0000-0002-2182-8291","observed_orcids":["https://orcid.org/0000-0002-2182-8291"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arman Zharmagambetov","raw_affiliation_strings":["FAIR @ Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR @ Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026557666","display_name":"Aaron Grattafiori","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Aaron Grattafiori","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127851377","display_name":"Chuan Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Guo","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010790447","display_name":"Kamalika Chaudhuri","orcid":"https://orcid.org/0000-0001-9646-7710","observed_orcids":["https://orcid.org/0000-0001-9646-7710"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamalika Chaudhuri","raw_affiliation_strings":["FAIR, Meta and UCSD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta and UCSD","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":51.1523,"has_fulltext":true,"cited_by_count":139,"citation_normalized_percentile":{"value":0.998958,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"22436","last_page":"22458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9926999807357788,"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":0.9926999807357788,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.0044999998062849045,"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":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8820000290870667},{"id":"https://openalex.org/keywords/web-agents","display_name":"web agents","score":0.7919999957084656},{"id":"https://openalex.org/keywords/artificial-intelligence-security","display_name":"AI security","score":0.5550000071525574},{"id":"https://openalex.org/keywords/security-benchmarking","display_name":"security benchmarking","score":0.7480000257492065},{"id":"https://openalex.org/keywords/deception-attacks","display_name":"deception attacks","score":0.49000000953674316},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6000000238418579},{"id":"https://openalex.org/keywords/security-assessment","display_name":"security analysis","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6531000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5680999755859375},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3059000074863434},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C527648132","wikidata":"https://www.wikidata.org/wiki/Q189900","display_name":"Information security","level":2,"score":0.24879999458789825}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-0666","doi":"https://doi.org/10.52202/085713-0666","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0666","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.18575","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.18575","pdf_url":"https://arxiv.org/pdf/2504.18575","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.18575","doi":"https://doi.org/10.48550/arxiv.2504.18575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.18575","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:2504.18575","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.18575","pdf_url":"https://arxiv.org/pdf/2504.18575","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W7196941018.pdf","grobid_xml":"https://content.openalex.org/works/W7196941018.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W4380353722","https://openalex.org/W4385327683","https://openalex.org/W4385374425","https://openalex.org/W4387800098","https://openalex.org/W4391766701","https://openalex.org/W4395064704","https://openalex.org/W4396239636","https://openalex.org/W4399838044","https://openalex.org/W4401066072","https://openalex.org/W4402667024","https://openalex.org/W4402670146","https://openalex.org/W4402671629","https://openalex.org/W4403564329","https://openalex.org/W4403851788","https://openalex.org/W4403884175","https://openalex.org/W4403885104","https://openalex.org/W4404260063","https://openalex.org/W4404330874","https://openalex.org/W4409150456","https://openalex.org/W4412944780","https://openalex.org/W4412945641","https://openalex.org/W4415795271","https://openalex.org/W4416052590","https://openalex.org/W4416549384","https://openalex.org/W4417315191","https://openalex.org/W7128378279"],"related_works":["https://openalex.org/W4415796822","https://openalex.org/W7201968379","https://openalex.org/W7160601009","https://openalex.org/W7127947320","https://openalex.org/W7197037656","https://openalex.org/W7084582695","https://openalex.org/W7160092587","https://openalex.org/W7197038096","https://openalex.org/W7170675441","https://openalex.org/W7077046559"],"abstract_inverted_index":{"Autonomous":[0],"UI":[1],"agents":[2,56,155],"powered":[3],"by":[4,13,38,61,125,171],"AI":[5,114],"have":[6],"tremendous":[7],"potential":[8,32],"to":[9,42,148,158],"boost":[10],"human":[11],"productivity":[12],"automating":[14],"routine":[15],"tasks":[16],"such":[17],"as":[18],"filing":[19],"taxes":[20],"and":[21],"paying":[22],"bills.":[23],"However,":[24],"a":[25,91,138],"major":[26],"challenge":[27],"in":[28,54,130,146],"unlocking":[29],"their":[30,46],"full":[31],"is":[33,36],"security,":[34],"which":[35],"exacerbated":[37],"the":[39,59,67,151,161,166],"agent's":[40],"ability":[41],"take":[43],"action":[44],"on":[45],"user's":[47],"behalf.":[48],"Existing":[49],"tests":[50],"for":[51,83,96],"prompt":[52],"injections":[53,129],"web":[55,85],"either":[57],"over-simplify":[58],"threat":[60],"testing":[62],"unrealistic":[63],"scenarios":[64],"or":[65,72],"giving":[66],"attacker":[68,162],"too":[69],"much":[70],"power,":[71],"look":[73],"at":[74],"single-step":[75],"isolated":[76],"tasks.":[77],"To":[78],"more":[79],"accurately":[80],"measure":[81],"progress":[82],"secure":[84],"agents,":[86],"we":[87],"introduce":[88],"WASP":[89,109],"--":[90,164],"new":[92],"publicly":[93],"available":[94],"benchmark":[95],"end-to-end":[97,135],"evaluation":[98,136],"of":[99,150,169],"Web":[100],"Agent":[101],"Security":[102],"against":[103],"Prompt":[104],"injection":[105],"attacks.":[106],"Evaluating":[107],"with":[108,118],"shows":[110],"that":[111],"even":[112,153],"top-tier":[113],"models,":[115],"including":[116],"those":[117],"advanced":[119],"reasoning":[120],"capabilities,":[121],"can":[122],"be":[123],"deceived":[124],"simple,":[126],"low-effort":[127],"human-written":[128],"very":[131],"realistic":[132],"scenarios.":[133],"Our":[134],"reveals":[137],"previously":[139],"unobserved":[140],"insight:":[141],"while":[142],"attacks":[143],"partially":[144],"succeed":[145],"up":[147],"86%":[149],"case,":[152],"state-of-the-art":[154],"often":[156],"struggle":[157],"fully":[159],"complete":[160],"goals":[163],"highlighting":[165],"current":[167],"state":[168],"security":[170],"incompetence.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":113},{"year":2025,"cited_by_count":26}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-07T00:00:00"}
