{"id":"https://openalex.org/W4409657529","doi":"https://doi.org/10.1145/3696410.3714632","title":"You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense","display_name":"You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657529","doi":"https://doi.org/10.1145/3696410.3714632"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714632","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714632","source":null,"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 ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714632","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117243276","display_name":"Wuyuao Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wuyuao Mai","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054807919","display_name":"Geng Hong","orcid":"https://orcid.org/0000-0003-1811-9432"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Geng Hong","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040129387","display_name":"Pei Chen","orcid":"https://orcid.org/0009-0001-8088-316X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074846459","display_name":"Xudong Pan","orcid":"https://orcid.org/0000-0003-1394-0395"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Pan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101694986","display_name":"Baojun Liu","orcid":"https://orcid.org/0000-0002-9032-8063"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baojun Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017552210","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0003-0726-9996"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067799841","display_name":"Haixin Duan","orcid":"https://orcid.org/0000-0003-0083-733X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixin Duan","raw_affiliation_strings":["Quancheng Laboratory, Jinan, China and Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Quancheng Laboratory, Jinan, China and Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052437722","display_name":"Min Yang","orcid":"https://orcid.org/0000-0001-9714-5545"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5117243276"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10261008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"872","last_page":"883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9864000082015991,"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9864000082015991,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9692999720573425,"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/degradation","display_name":"Degradation (telecommunications)","score":0.7982755303382874},{"id":"https://openalex.org/keywords/environmental-degradation","display_name":"Environmental degradation","score":0.4693601727485657},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.39721617102622986},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3771982789039612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3598176836967468},{"id":"https://openalex.org/keywords/natural-resource-economics","display_name":"Natural resource economics","score":0.3572985529899597},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.21942555904388428},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15305042266845703},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.08521056175231934},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0734323263168335}],"concepts":[{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.7982755303382874},{"id":"https://openalex.org/C198428699","wikidata":"https://www.wikidata.org/wiki/Q1334780","display_name":"Environmental degradation","level":2,"score":0.4693601727485657},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.39721617102622986},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3771982789039612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3598176836967468},{"id":"https://openalex.org/C175605778","wikidata":"https://www.wikidata.org/wiki/Q3299701","display_name":"Natural resource economics","level":1,"score":0.3572985529899597},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.21942555904388428},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15305042266845703},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.08521056175231934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0734323263168335}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714632","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714632","source":null,"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 ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714632","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714632","source":null,"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 ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2315473009","display_name":null,"funder_award_id":"2024YFF0618800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G348829379","display_name":null,"funder_award_id":"U2436207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G608220617","display_name":null,"funder_award_id":"2024YFF0618800","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8864147625","display_name":null,"funder_award_id":"21TQ1400100","funder_id":"https://openalex.org/F4320321851","funder_display_name":"Fudan University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657529.pdf","grobid_xml":"https://content.openalex.org/works/W4409657529.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4389523771","https://openalex.org/W4389617257","https://openalex.org/W4402671155"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2534928293","https://openalex.org/W2150099345","https://openalex.org/W2160318243","https://openalex.org/W1490077415","https://openalex.org/W3004580327","https://openalex.org/W2182874356","https://openalex.org/W3034806817","https://openalex.org/W4214933169","https://openalex.org/W4385487306"],"abstract_inverted_index":{"With":[0],"the":[1,42,76,90,107],"rise":[2],"of":[3,45,80,92],"generative":[4],"large":[5],"language":[6],"models":[7,14],"(LLMs)":[8],"like":[9],"LLaMA":[10],"and":[11,20,59,78,112],"ChatGPT,":[12],"these":[13,66,73],"have":[15,47],"significantly":[16],"transformed":[17],"daily":[18],"life":[19],"work":[21],"by":[22],"providing":[23],"advanced":[24],"insights.":[25],"However,":[26],"as":[27,55],"jailbreak":[28],"attacks":[29],"continue":[30],"to":[31,64],"circumvent":[32],"built-in":[33],"safety":[34,43,111],"mechanisms,":[35],"exploiting":[36],"carefully":[37],"crafted":[38],"scenarios":[39],"or":[40],"tokens,":[41],"risks":[44],"LLMs":[46,81],"come":[48],"into":[49],"focus.":[50],"While":[51],"numerous":[52],"defense":[53,93],"strategies-such":[54],"prompt":[56],"detection,":[57],"modification,":[58],"model":[60],"fine-tuning-have":[61],"been":[62],"proposed":[63],"counter":[65],"attacks,":[67],"a":[68,103],"critical":[69],"question":[70],"arises:":[71],"do":[72],"defenses":[74],"compromise":[75],"utility":[77],"usability":[79],"for":[82],"legitimate":[83],"users?":[84],"Existing":[85],"research":[86],"predominantly":[87],"focuses":[88],"on":[89,100],"effectiveness":[91],"strategies":[94],"without":[95],"thoroughly":[96],"examining":[97],"their":[98],"impact":[99],"performance,":[101],"leaving":[102],"gap":[104],"in":[105],"understanding":[106],"trade-offs":[108],"between":[109],"LLM":[110],"performance.":[113]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
