{"id":"https://openalex.org/W4405182525","doi":"https://doi.org/10.1145/3658644.3690322","title":"<scp>Legilimens:</scp> Practical and Unified Content Moderation for Large Language Model Services","display_name":"<scp>Legilimens:</scp> Practical and Unified Content Moderation for Large Language Model Services","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4405182525","doi":"https://doi.org/10.1145/3658644.3690322"},"language":"en","primary_location":{"id":"doi:10.1145/3658644.3690322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690322","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690322","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103472853","display_name":"Jialin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-9659-5259","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080527605","display_name":"Jiangyi Deng","orcid":"https://orcid.org/0000-0002-8262-7813"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyi Deng","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-8262-7813","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084791178","display_name":"Shengyuan Pang","orcid":"https://orcid.org/0009-0002-7945-3987"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyuan Pang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0002-7945-3987","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015275781","display_name":"Yanjiao Chen","orcid":"https://orcid.org/0000-0002-1382-0679"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjiao Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-1382-0679","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011203946","display_name":"Jiayang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayang Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0002-2557-2438","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044549752","display_name":"Xinfeng Li","orcid":"https://orcid.org/0000-0002-9686-4369"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-9686-4369","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060351020","display_name":"Wenyuan Xu","orcid":"https://orcid.org/0000-0002-5043-9148"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyuan Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-5043-9148","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1151","last_page":"1165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998000264167786,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998000264167786,"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/T13157","display_name":"Cancer-related gene regulation","score":0.9503999948501587,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.9152178168296814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6896435022354126},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6798125505447388},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.5941546559333801},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5391291975975037},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4910423755645752},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.32621335983276367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1521933376789093},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13931164145469666},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08495432138442993}],"concepts":[{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.9152178168296814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6896435022354126},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6798125505447388},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.5941546559333801},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5391291975975037},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4910423755645752},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.32621335983276367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1521933376789093},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13931164145469666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08495432138442993},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658644.3690322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690322","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3658644.3690322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690322","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5994516692","display_name":null,"funder_award_id":"61925109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405182525.pdf","grobid_xml":"https://content.openalex.org/works/W4405182525.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W80056832","https://openalex.org/W2740168486","https://openalex.org/W2971173235","https://openalex.org/W2998617917","https://openalex.org/W3008694996","https://openalex.org/W3034951181","https://openalex.org/W3101118213","https://openalex.org/W4283170666","https://openalex.org/W4382318449","https://openalex.org/W4385764438","https://openalex.org/W4389524426","https://openalex.org/W4389713766","https://openalex.org/W4389736946"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2772323916"],"abstract_inverted_index":{"Given":[0],"the":[1,57,112,127],"societal":[2],"impact":[3],"of":[4,114,129],"unsafe":[5],"content":[6,30,64,84,92],"generated":[7],"by":[8,35,69],"large":[9],"language":[10],"models":[11,41,46],"(LLMs),":[12],"ensuring":[13],"that":[14,60],"LLM":[15,26,96],"services":[16],"comply":[17],"with":[18],"safety":[19],"standards":[20],"is":[21],"a":[22,88,122],"crucial":[23],"concern":[24],"for":[25,56,80,95],"service":[27],"providers.":[28],"Common":[29],"moderation":[31,65,93],"methods":[32,134],"are":[33,42],"limited":[34],"an":[36],"effectiveness-and-efficiency":[37],"dilemma,":[38],"where":[39],"simple":[40],"fragile":[43],"while":[44],"sophisticated":[45],"consume":[47],"excessive":[48],"computational":[49],"resources.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,120],"reveal":[55],"first":[58],"time":[59],"effective":[61],"and":[62,90,104],"efficient":[63],"can":[66],"be":[67],"achieved":[68],"extracting":[70],"conceptual":[71],"features":[72,101],"from":[73],"chat-oriented":[74],"LLMs,":[75],"despite":[76],"their":[77],"initial":[78],"fine-tuning":[79],"conversation":[81],"rather":[82],"than":[83],"moderation.":[85],"We":[86],"propose":[87],"practical":[89],"unified":[91],"framework":[94,123],"services,":[97],"named":[98],"Legilimens,":[99],"which":[100],"both":[102],"effectiveness":[103],"efficiency.":[105],"Our":[106],"red-team":[107],"model-based":[108],"data":[109],"augmentation":[110],"enhances":[111],"robustness":[113],"Legilimens":[115,130],"against":[116],"state-of-the-art":[117],"jailbreaking.":[118],"Additionally,":[119],"develop":[121],"to":[124,132],"theoretically":[125],"analyze":[126],"cost-effectiveness":[128],"compared":[131],"other":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
