{"id":"https://openalex.org/W7162454559","doi":"https://doi.org/10.48550/arxiv.2605.25707","title":"AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions","display_name":"AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162454559","doi":"https://doi.org/10.48550/arxiv.2605.25707"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25707","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.2605.25707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137015974","display_name":"Jingwei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137052087","display_name":"Jianing Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jianing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137039157","display_name":"Yuanyi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuanyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137001236","display_name":"Tongliang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tongliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137067230","display_name":"Xia HU","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"HU, Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137019962","display_name":"Bo Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Bo","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18979999423027039,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18979999423027039,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.10580000281333923,"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":0.10300000011920929,"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/robustness","display_name":"Robustness (evolution)","score":0.7803000211715698},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6075999736785889},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.45210000872612},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.4068000018596649},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.36559998989105225},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.3555999994277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996000051498413},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7803000211715698},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6075999736785889},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25707","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.2605.25707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25707","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":[{"score":0.8055260181427002,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"computer":[1],"use":[2],"agents":[3,55,95,115],"that":[4,92,98,129],"powered":[5],"by":[6],"multimodal":[7],"large":[8],"language":[9],"models":[10,157],"(MLLMs)":[11],"are":[12,26,160],"emerging":[13],"as":[14],"capable":[15],"assistants":[16],"for":[17,142],"completing":[18],"complex":[19],"digital":[20],"workflows.":[21],"However,":[22],"real-world":[23],"execution":[24,67],"environments":[25],"far":[27],"from":[28],"ideal:":[29],"pop-ups,":[30],"resolution":[31],"changes,":[32],"and":[33,41,96,116,138,145,158],"competing":[34],"applications":[35],"frequently":[36],"interfere":[37],"with":[38,134],"agent":[39],"perception":[40],"control.":[42],"We":[43,85],"introduce":[44],"AgentHijack,":[45],"a":[46,87,127],"benchmark":[47],"designed":[48],"to":[49,80],"evaluate":[50,86],"the":[51,60,66,112,118],"robustness":[52,121],"of":[53,89,102,114,120],"computer-use":[54],"under":[56],"common":[57,78],"corruptions,":[58],"where":[59],"uncertainties":[61],"in":[62,106],"dynamic":[63],"environment":[64,146],"disrupt":[65],"flow":[68],"without":[69],"direct":[70],"adversarial":[71],"intent.":[72],"Specifically,":[73],"AgentHijack":[74],"introduces":[75],"9":[76],"configurable":[77],"corruptions":[79],"replicate":[81],"realistic":[82],"imperfect":[83],"scenarios.":[84],"variety":[88],"desktop":[90],"tasks":[91],"utilize":[93],"MLLM-based":[94],"discover":[97],"even":[99],"minor":[100],"instances":[101],"corruption":[103],"can":[104],"result":[105],"substantial":[107],"performance":[108],"degradation,":[109],"which":[110],"emphasizes":[111],"fragility":[113],"underscores":[117],"necessity":[119],"evaluation.":[122],"Afterward,":[123],"we":[124],"propose":[125],"AgentHijack-Agent,":[126],"framework":[128],"integrates":[130],"an":[131,139],"action":[132],"generator":[133],"enhanced":[135],"grounding":[136],"capabilities":[137],"onlooker":[140],"responsible":[141],"behavior":[143],"summarization":[144],"checking.":[147],"Extensive":[148],"experiments":[149],"validate":[150],"its":[151],"effectiveness.":[152],"Our":[153],"code,":[154],"environment,":[155],"baseline":[156],"data":[159],"publicly":[161],"available":[162],"at:":[163],"https://AgentHijack.github.io.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}
