{"id":"https://openalex.org/W4413214047","doi":"https://doi.org/10.1145/3712255.3726687","title":"A Genetic Algorithm Framework for Jailbreaking Large Language Models","display_name":"A Genetic Algorithm Framework for Jailbreaking Large Language Models","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4413214047","doi":"https://doi.org/10.1145/3712255.3726687"},"language":"en","primary_location":{"id":"doi:10.1145/3712255.3726687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712255.3726687","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://run.unl.pt/bitstream/10362/187321/1/Genetic_Algorithm_Framework_for_Jailbreaking_LLM.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036813634","display_name":"Lorenzo Bonin","orcid":"https://orcid.org/0000-0003-4520-2426"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Lorenzo Bonin","raw_affiliation_strings":["University of Trieste, Trieste, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4520-2426","affiliations":[{"raw_affiliation_string":"University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119306176","display_name":"Lorenzo Cusin","orcid":null},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Cusin","raw_affiliation_strings":["University of Trieste, Trieste, Italy"],"raw_orcid":"https://orcid.org/0009-0005-4819-905X","affiliations":[{"raw_affiliation_string":"University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031604878","display_name":"Andrea De Lorenzo","orcid":"https://orcid.org/0000-0002-7628-7672"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea De Lorenzo","raw_affiliation_strings":["University of Trieste, Trieste, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7628-7672","affiliations":[{"raw_affiliation_string":"University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087976149","display_name":"Mauro Castelli","orcid":"https://orcid.org/0000-0002-8793-1451"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Mauro Castelli","raw_affiliation_strings":["Universidade Nova de Lisboa, Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-8793-1451","affiliations":[{"raw_affiliation_string":"Universidade Nova de Lisboa, Lisboa, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064452080","display_name":"Luca Manzoni","orcid":"https://orcid.org/0000-0001-6312-7728"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Manzoni","raw_affiliation_strings":["University of Trieste, Trieste, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6312-7728","affiliations":[{"raw_affiliation_string":"University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036813634"],"corresponding_institution_ids":["https://openalex.org/I142444530"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53035714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.979200005531311,"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"}},"topics":[{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.979200005531311,"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/computer-science","display_name":"Computer science","score":0.7257038354873657},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.49015936255455017},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42849284410476685},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3259187340736389},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1526530385017395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257038354873657},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.49015936255455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42849284410476685},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3259187340736389},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1526530385017395}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3712255.3726687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712255.3726687","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:run.unl.pt:10362/187321","is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/187321","pdf_url":"https://run.unl.pt/bitstream/10362/187321/1/Genetic_Algorithm_Framework_for_Jailbreaking_LLM.pdf","source":{"id":"https://openalex.org/S4306400678","display_name":"Universidade Nova de Lisboa's Repository (Universidade Nova de Lisboa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83558840","host_organization_name":"Universidade Nova de Lisboa","host_organization_lineage":["https://openalex.org/I83558840"],"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":"conferenceObject"},{"id":"pmh:oai:arts.units.it:11368/3115300","is_oa":false,"landing_page_url":"https://hdl.handle.net/11368/3115300","pdf_url":null,"source":{"id":"https://openalex.org/S4306402362","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:run.unl.pt:10362/187321","is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/187321","pdf_url":"https://run.unl.pt/bitstream/10362/187321/1/Genetic_Algorithm_Framework_for_Jailbreaking_LLM.pdf","source":{"id":"https://openalex.org/S4306400678","display_name":"Universidade Nova de Lisboa's Repository (Universidade Nova de Lisboa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83558840","host_organization_name":"Universidade Nova de Lisboa","host_organization_lineage":["https://openalex.org/I83558840"],"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":"conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413214047.pdf","grobid_xml":"https://content.openalex.org/works/W4413214047.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4391136507"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Despite":[0,41],"their":[1],"capabilities":[2],"to":[3,18,32,35,47,56],"generate":[4,57],"human-like":[5],"text":[6],"and":[7],"aid":[8],"in":[9],"various":[10],"tasks,":[11],"Large":[12],"Language":[13],"Models":[14],"(LLMs)":[15],"are":[16],"susceptible":[17],"misuse.":[19],"To":[20],"mitigate":[21],"this":[22],"risk,":[23],"many":[24],"LLMs":[25,44,82],"undergo":[26],"safety":[27,73],"alignment":[28],"or":[29,38,66],"refusal":[30],"training":[31],"allow":[33],"them":[34],"refuse":[36],"unsafe":[37,58],"unethical":[39],"requests.":[40],"these":[42],"measures,":[43],"remain":[45],"exposed":[46],"jailbreak":[48,85],"attacks\u2014i.e.,":[49],"adversarial":[50,67],"techniques":[51],"that":[52,69],"manipulate":[53],"the":[54,71,78],"models":[55],"outputs.":[59],"Jailbreaking":[60],"typically":[61],"involves":[62],"crafting":[63],"specific":[64],"prompts":[65],"inputs":[68],"bypass":[70],"models'":[72],"mechanisms.":[74],"This":[75],"paper":[76],"examines":[77],"robustness":[79],"of":[80],"safety-aligned":[81],"against":[83],"adaptive":[84],"attacks,":[86],"focusing":[87],"on":[88],"a":[89],"genetic":[90],"algorithm-based":[91],"approach.":[92]},"counts_by_year":[],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-10T00:00:00"}
