{"id":"https://openalex.org/W4388850876","doi":"https://doi.org/10.1145/3605760.3623764","title":"Jailbreaker in Jail: Moving Target Defense for Large Language Models","display_name":"Jailbreaker in Jail: Moving Target Defense for Large Language Models","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388850876","doi":"https://doi.org/10.1145/3605760.3623764"},"language":"en","primary_location":{"id":"doi:10.1145/3605760.3623764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605760.3623764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Workshop on Moving Target Defense","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076545839","display_name":"Bocheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bocheng Chen","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"raw_orcid":"https://orcid.org/0009-0001-0471-7063","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102742592","display_name":"Advait Paliwal","orcid":"https://orcid.org/0009-0000-3815-0184"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Advait Paliwal","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"raw_orcid":"https://orcid.org/0009-0000-3815-0184","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042277127","display_name":"Qiben Yan","orcid":"https://orcid.org/0000-0001-6272-7668"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiben Yan","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"raw_orcid":"https://orcid.org/0000-0001-6272-7668","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076545839"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":3.9152,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94922981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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":0.9993000030517578,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10951","display_name":"Cryptographic Implementations and Security","score":0.9714000225067139,"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/adversarial-system","display_name":"Adversarial system","score":0.9212072491645813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6309472322463989},{"id":"https://openalex.org/keywords/chatbot","display_name":"Chatbot","score":0.5819628238677979},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.557496190071106},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5043586492538452},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4904136657714844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3036094009876251},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17427930235862732}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9212072491645813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309472322463989},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.5819628238677979},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.557496190071106},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5043586492538452},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4904136657714844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3036094009876251},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17427930235862732}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605760.3623764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605760.3623764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Workshop on Moving Target Defense","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4106033645","display_name":null,"funder_award_id":"CNS-1950171, CNS-2310207","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4226278401","https://openalex.org/W4308222467","https://openalex.org/W4308222494"],"related_works":["https://openalex.org/W4383501580","https://openalex.org/W4214931137","https://openalex.org/W4313813117","https://openalex.org/W4382052417","https://openalex.org/W3192088754","https://openalex.org/W4387007686","https://openalex.org/W3084631705","https://openalex.org/W3176146353","https://openalex.org/W4293646425","https://openalex.org/W4379781060"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,125],"(LLMs),":[3],"known":[4],"for":[5],"their":[6],"capability":[7],"in":[8],"understanding":[9],"and":[10,57,95],"following":[11],"instructions,":[12],"are":[13],"vulnerable":[14],"to":[15,27,36,41,72,99,141,152],"adversarial":[16,48,89,128],"attacks.":[17,90],"Researchers":[18],"have":[19],"found":[20],"that":[21,76],"current":[22],"commercial":[23],"LLMs":[24],"either":[25],"fail":[26,35],"be":[28,37],"\"harmless\"":[29],"by":[30,39],"presenting":[31],"unethical":[32],"answers,":[33],"or":[34,103],"\"helpful\"":[38],"refusing":[40],"offer":[42],"meaningful":[43],"answers":[44,75],"when":[45],"faced":[46],"with":[47,78,126],"queries.":[49,129],"To":[50],"strike":[51],"a":[52,61,93],"balance":[53],"between":[54],"being":[55],"helpful":[56],"harmless,":[58],"we":[59],"design":[60,92],"moving":[62],"target":[63],"defense":[64],"(MTD)":[65],"enhanced":[66],"LLM":[67,132],"system.":[68],"The":[69],"system":[70,133],"aims":[71],"deliver":[73],"non-toxic":[74],"align":[77],"outputs":[79,114],"from":[80,115,139,150],"multiple":[81],"model":[82,98],"candidates,":[83],"making":[84],"them":[85],"more":[86],"robust":[87],"against":[88],"We":[91,118],"query":[94],"output":[96],"analysis":[97],"filter":[100],"out":[101],"unsafe":[102],"non-responsive":[104],"answers.":[105],"%to":[106],"achieve":[107],"the":[108,135,146],"two":[109],"objectives":[110],"of":[111],"randomly":[112],"selecting":[113],"different":[116],"LLMs.":[117],"evaluate":[119],"over":[120],"8":[121],"most":[122],"recent":[123],"chatbot":[124],"state-of-the-art":[127],"Our":[130],"MTD-enhanced":[131],"reduces":[134],"attack":[136],"success":[137],"rate":[138,149],"37.5%":[140],"0%.":[142,153],"Meanwhile,":[143],"it":[144],"decreases":[145],"response":[147],"refusal":[148],"50%":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}