{"id":"https://openalex.org/W4410553894","doi":"https://doi.org/10.1007/s43681-025-00750-4","title":"RogueGPT: transforming ChatGPT-4 into a rogue AI with dis-ethical tuning","display_name":"RogueGPT: transforming ChatGPT-4 into a rogue AI with dis-ethical tuning","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4410553894","doi":"https://doi.org/10.1007/s43681-025-00750-4"},"language":"en","primary_location":{"id":"doi:10.1007/s43681-025-00750-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43681-025-00750-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43681-025-00750-4.pdf","source":{"id":"https://openalex.org/S4210170699","display_name":"AI and Ethics","issn_l":"2730-5953","issn":["2730-5953","2730-5961"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI and Ethics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s43681-025-00750-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086122900","display_name":"Alessio Buscemi","orcid":"https://orcid.org/0000-0003-2762-4123"},"institutions":[{"id":"https://openalex.org/I4210112527","display_name":"Luxembourg Institute of Science and Technology","ror":"https://ror.org/01t178j62","country_code":"LU","type":"education","lineage":["https://openalex.org/I4210112527"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Alessio Buscemi","raw_affiliation_strings":["Luxembourg Institute of Science and Technology, Belvaux, Luxembourg"],"affiliations":[{"raw_affiliation_string":"Luxembourg Institute of Science and Technology, Belvaux, Luxembourg","institution_ids":["https://openalex.org/I4210112527"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037164344","display_name":"Daniele Proverbio","orcid":"https://orcid.org/0000-0002-0122-479X"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Proverbio","raw_affiliation_strings":["University of Trento, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086122900"],"corresponding_institution_ids":["https://openalex.org/I4210112527"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.6977,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76283026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"5","issue":"5","first_page":"4945","last_page":"4966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9939000010490417,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4031328558921814},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.3789132535457611},{"id":"https://openalex.org/keywords/engineering-ethics","display_name":"Engineering ethics","score":0.3295910358428955},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1662609577178955}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4031328558921814},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3789132535457611},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.3295910358428955},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1662609577178955}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s43681-025-00750-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43681-025-00750-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43681-025-00750-4.pdf","source":{"id":"https://openalex.org/S4210170699","display_name":"AI and Ethics","issn_l":"2730-5953","issn":["2730-5953","2730-5961"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI and Ethics","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/455993","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/455993","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s43681-025-00750-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43681-025-00750-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43681-025-00750-4.pdf","source":{"id":"https://openalex.org/S4210170699","display_name":"AI and Ethics","issn_l":"2730-5953","issn":["2730-5953","2730-5961"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI and Ethics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322275","display_name":"Universit\u00e0 degli Studi di Trento","ror":"https://ror.org/05trd4x28"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410553894.pdf","grobid_xml":"https://content.openalex.org/works/W4410553894.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W648152870","https://openalex.org/W2064675550","https://openalex.org/W2119591566","https://openalex.org/W2572775696","https://openalex.org/W2897042519","https://openalex.org/W2950813464","https://openalex.org/W2957285709","https://openalex.org/W2968594320","https://openalex.org/W2968870211","https://openalex.org/W2971173235","https://openalex.org/W3001807593","https://openalex.org/W3085190015","https://openalex.org/W3100279624","https://openalex.org/W3100355250","https://openalex.org/W3133702157","https://openalex.org/W3180145931","https://openalex.org/W4253935475","https://openalex.org/W4292166681","https://openalex.org/W4319661244","https://openalex.org/W4366588626","https://openalex.org/W4376133468","https://openalex.org/W4388440553","https://openalex.org/W4388858734","https://openalex.org/W4389617257","https://openalex.org/W4390956858","https://openalex.org/W4400315206","https://openalex.org/W4400484590","https://openalex.org/W4405181600","https://openalex.org/W6600137863","https://openalex.org/W6600466347","https://openalex.org/W6602503091","https://openalex.org/W6604820196","https://openalex.org/W6702248584","https://openalex.org/W6763240421","https://openalex.org/W6780161852"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W4220667126","https://openalex.org/W2077865380","https://openalex.org/W3006817050","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512"],"abstract_inverted_index":{"Abstract":[0],"The":[1,107],"ethical":[2,23,135,161],"implications":[3],"and":[4,38,105,131,142,147,160],"potentials":[5],"for":[6,126],"misuse":[7],"of":[8,25,53,72,109,134,144,158,172],"Generative":[9],"Artificial":[10],"Intelligence":[11],"are":[12],"increasingly":[13],"worrying":[14,59],"topics.":[15],"This":[16,49,168],"paper":[17,169],"explores":[18],"how":[19],"easily":[20],"the":[21,46,94,122,128,132,140,148,156],"default":[22],"guardrails":[24],"ChatGPT,":[26,54],"using":[27],"its":[28,76,115],"latest":[29],"customization":[30],"features,":[31],"can":[32,41],"be":[33,42,85],"bypassed":[34],"by":[35,45,64,164],"simple":[36],"prompts":[37],"fine-tuning,":[39],"that":[40,151],"effortlessly":[43],"accessed":[44],"broad":[47],"public.":[48],"malevolently":[50],"altered":[51],"version":[52],"nicknamed":[55],"\u201cRogueGPT\u201d,":[56],"responded":[57],"with":[58,114],"behaviours,":[60],"beyond":[61],"those":[62],"triggered":[63],"jailbreak":[65],"prompts.":[66],"We":[67,137],"conduct":[68],"an":[69],"empirical":[70],"study":[71],"RogueGPT":[73],"responses,":[74],"assessing":[75],"flexibility":[77],"in":[78],"answering":[79],"questions":[80],"pertaining":[81],"to":[82],"what":[83],"should":[84],"disallowed":[86],"usage.":[87],"Our":[88],"findings":[89],"raise":[90],"significant":[91],"concerns":[92],"about":[93,97],"model\u2019s":[95],"knowledge":[96],"topics":[98],"like":[99],"illegal":[100],"drug":[101],"production,":[102],"torture":[103],"methods":[104],"terrorism.":[106],"ease":[108],"driving":[110],"ChatGPT":[111],"astray,":[112],"coupled":[113],"global":[116],"accessibility,":[117],"highlights":[118],"severe":[119],"issues":[120],"regarding":[121],"data":[123],"quality":[124],"used":[125],"training":[127],"foundational":[129],"model":[130],"implementation":[133],"safeguards.":[136],"thus":[138],"underline":[139],"responsibilities":[141],"dangers":[143],"user-driven":[145],"modifications,":[146],"broader":[149],"effects":[150],"these":[152],"may":[153],"have":[154],"on":[155],"design":[157],"safeguarding":[159],"modules":[162],"implemented":[163],"AI":[165],"programmers.":[166],"Disclaimer.":[167],"contains":[170],"examples":[171],"harmful":[173],"language.":[174],"Reader":[175],"discretion":[176],"is":[177],"recommended.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-05-21T00:00:00"}
