{"id":"https://openalex.org/W7140086443","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.33","title":"When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models","display_name":"When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140086443","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.33"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-srw.33","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.33","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.33","pdf_url":"https://aclanthology.org/2026.eacl-srw.33.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.eacl-srw.33.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130370343","display_name":"Zafir Shamsi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zafir Shamsi","raw_affiliation_strings":["AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130335217","display_name":"Nikhil Chekuru","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Chekuru","raw_affiliation_strings":["AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130402660","display_name":"Zachary Guzman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zachary Guzman","raw_affiliation_strings":["AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130379656","display_name":"Shivank Garg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shivank Garg","raw_affiliation_strings":["AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.14163717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9761000275611877,"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":0.9761000275611877,"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":0.01119999960064888,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.007600000128149986,"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-optimization","display_name":"prompt optimization","score":0.9179999828338623},{"id":"https://openalex.org/keywords/jailbreaking","display_name":"jailbreaking","score":0.9300000071525574},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8989999890327454},{"id":"https://openalex.org/keywords/red-teaming","display_name":"red teaming","score":0.9269999861717224},{"id":"https://openalex.org/keywords/adaptive-attacks","display_name":"adaptive attacks","score":0.5460000038146973},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.4959999918937683},{"id":"https://openalex.org/keywords/ai-safety","display_name":"AI safety","score":0.31200000643730164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6050000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24940000474452972},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.23729999363422394},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23649999499320984},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.23109999299049377}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-srw.33","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.33","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.33","pdf_url":"https://aclanthology.org/2026.eacl-srw.33.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-srw.33","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.33","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.33","pdf_url":"https://aclanthology.org/2026.eacl-srw.33.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140086443.pdf","grobid_xml":"https://content.openalex.org/works/W7140086443.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166807713","https://openalex.org/W4385894687","https://openalex.org/W4416936422","https://openalex.org/W4404782533","https://openalex.org/W4401042259","https://openalex.org/W7140092603","https://openalex.org/W7166859151","https://openalex.org/W6941431699","https://openalex.org/W7166891461","https://openalex.org/W4402671743"],"abstract_inverted_index":{"Zafir":[0],"Shamsi,":[1],"Nikhil":[2],"Chekuru,":[3],"Zachary":[4],"Guzman,":[5],"Shivank":[6],"Garg.":[7],"Proceedings":[8],"of":[9,13,17],"the":[10,14,18],"19th":[11],"Conference":[12],"European":[15],"Chapter":[16],"Association":[19],"for":[20],"Computational":[21],"Linguistics":[22],"(Volume":[23],"4:":[24],"Student":[25],"Research":[26],"Workshop).":[27],"2026.":[28]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}
