{"id":"https://openalex.org/W7204166141","doi":"https://doi.org/10.13140/rg.2.2.23737.53600","title":"Emergent Exploitation Without Adversarial Instruction: A Case Study of Autonomous Sandbox Escape and Third Party Compromise During AI Model Evaluation","display_name":"Emergent Exploitation Without Adversarial Instruction: A Case Study of Autonomous Sandbox Escape and Third Party Compromise During AI Model Evaluation","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204166141","doi":"https://doi.org/10.13140/rg.2.2.23737.53600"},"language":"en","primary_location":{"id":"doi:10.13140/rg.2.2.23737.53600","doi":"https://doi.org/10.13140/rg.2.2.23737.53600","is_oa":true,"landing_page_url":"https://doi.org/10.13140/rg.2.2.23737.53600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.13140/rg.2.2.23737.53600","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147344842","display_name":"Shumail Seyar","orcid":"https://orcid.org/0009-0008-7067-2423","observed_orcids":["https://orcid.org/0009-0008-7067-2423"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shumail Seyar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147344842"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68793439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8130000233650208,"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":0.8130000233650208,"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":0.13490000367164612,"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/T10734","display_name":"Information and Cyber Security","score":0.026200000196695328,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/emergent-behavior","display_name":"emergent behavior","score":0.6430000066757202},{"id":"https://openalex.org/keywords/sandbox-escape","display_name":"sandbox escape","score":0.7570000290870667},{"id":"https://openalex.org/keywords/ai-model-evaluation","display_name":"AI model evaluation","score":0.9340000152587891},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.625}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7998999953269958},{"id":"https://openalex.org/C167981075","wikidata":"https://www.wikidata.org/wiki/Q2667186","display_name":"Sandbox (software development)","level":2,"score":0.7031000256538391},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.6740000247955322},{"id":"https://openalex.org/C2983583741","wikidata":"https://www.wikidata.org/wiki/Q16785388","display_name":"Third party","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5285999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49549999833106995},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.37940001487731934},{"id":"https://openalex.org/C190253527","wikidata":"https://www.wikidata.org/wiki/Q295354","display_name":"Law and economics","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C109913982","wikidata":"https://www.wikidata.org/wiki/Q208330","display_name":"Stalemate","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C86387943","wikidata":"https://www.wikidata.org/wiki/Q1062245","display_name":"Res judicata","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2632000148296356},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C194541083","wikidata":"https://www.wikidata.org/wiki/Q457174","display_name":"Workaround","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13140/rg.2.2.23737.53600","doi":"https://doi.org/10.13140/rg.2.2.23737.53600","is_oa":true,"landing_page_url":"https://doi.org/10.13140/rg.2.2.23737.53600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.13140/rg.2.2.23737.53600","doi":"https://doi.org/10.13140/rg.2.2.23737.53600","is_oa":true,"landing_page_url":"https://doi.org/10.13140/rg.2.2.23737.53600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6140545010566711}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2026-08-26T00:00:00"}
