{"id":"https://openalex.org/W4405183113","doi":"https://doi.org/10.1145/3658644.3690291","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","display_name":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4405183113","doi":"https://doi.org/10.1145/3658644.3690291"},"language":"en","primary_location":{"id":"doi:10.1145/3658644.3690291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690291","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/10.1145/3658644.3690291","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiawen Shi","orcid":"https://orcid.org/0009-0007-6088-509X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Shi","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0007-6088-509X","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014040279","display_name":"Zenghui Yuan","orcid":"https://orcid.org/0000-0002-2839-9127"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenghui Yuan","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2839-9127","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yinuo Liu","orcid":"https://orcid.org/0009-0000-0384-5138"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinuo Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-0384-5138","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103549861","display_name":"Yue Huang","orcid":"https://orcid.org/0000-0002-8315-7972"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Huang","raw_affiliation_strings":["University of Notre Dame, South Bend, USA"],"raw_orcid":"https://orcid.org/0000-0002-8315-7972","affiliations":[{"raw_affiliation_string":"University of Notre Dame, South Bend, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693194","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0001-8747-9912"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8747-9912","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015105117","display_name":"Lichao Sun","orcid":"https://orcid.org/0000-0003-1539-7939"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["Lehigh University, Bethlehem, USA"],"raw_orcid":"https://orcid.org/0000-0003-1539-7939","affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009102659","display_name":"Neil Zhenqiang Gong","orcid":"https://orcid.org/0000-0002-9900-9309"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Zhenqiang Gong","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0002-9900-9309","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"660","last_page":"674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9943000078201294,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9926000237464905,"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/perplexity","display_name":"Perplexity","score":0.9522452354431152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770506739616394},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6541392803192139},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6522597670555115},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6121686100959778},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48108336329460144},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4675178825855255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4542525112628937},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44121986627578735},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08326104283332825}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9522452354431152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770506739616394},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6541392803192139},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6522597670555115},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6121686100959778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48108336329460144},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4675178825855255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4542525112628937},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44121986627578735},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08326104283332825},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658644.3690291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690291","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:10.1145/3658644.3690291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690291","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/G6357611846","display_name":null,"funder_award_id":"62476107","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G664739573","display_name":null,"funder_award_id":"62476107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405183113.pdf","grobid_xml":"https://content.openalex.org/works/W4405183113.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2350778671","https://openalex.org/W3189812816","https://openalex.org/W4212774754","https://openalex.org/W4388886073","https://openalex.org/W4405181744"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"LLM-as-a-Judge":[0,21,64],"uses":[1],"a":[2,13,18,53,92],"large":[3],"language":[4],"model":[5],"(LLM)":[6],"to":[7,49,96,130],"select":[8],"the":[9,66,122,136,172],"best":[10],"response":[11,61,68],"from":[12],"set":[14],"of":[15,138],"candidates":[16],"for":[17,69,175],"given":[19],"question.":[20],"has":[22],"many":[23],"applications":[24],"such":[25,62,84],"as":[26,86],"LLM-powered":[27,145],"search,":[28,146],"reinforcement":[29],"learning":[30],"with":[31],"AI":[32],"feedback":[33],"(RLAIF),":[34],"and":[35,90,109,125,148,160],"tool":[36,149],"selection.":[37,150],"In":[38],"this":[39],"work,":[40],"we":[41,81,152],"propose":[42,91],"JudgeDeceiver,":[43],"an":[44,58,70,87],"optimization-based":[45],"prompt":[46,116],"injection":[47,117],"attack":[48],"LLM-as-a-Judge.":[50],"JudgeDeceiver":[51,139],"injects":[52],"carefully":[54],"crafted":[55],"sequence":[56,85],"into":[57],"attacker-controlled":[59],"candidate":[60,67,77],"that":[63,104,119],"selects":[65],"attacker-chosen":[71],"question":[72],"no":[73],"matter":[74],"what":[75],"other":[76],"responses":[78],"are.":[79],"Specifically,":[80],"formulate":[82],"finding":[83],"optimization":[88],"problem":[89],"gradient":[93],"based":[94],"method":[95],"approximately":[97],"solve":[98],"it.":[99],"Our":[100,164],"extensive":[101],"evaluation":[102],"shows":[103],"JudgeDeceive":[105],"is":[106,110],"highly":[107],"effective,":[108],"much":[111],"more":[112],"effective":[113],"than":[114],"existing":[115],"attacks":[118,127],"manually":[120],"craft":[121],"injected":[123],"sequences":[124],"jailbreak":[126],"when":[128],"extended":[129],"our":[131],"problem.":[132],"We":[133],"also":[134],"show":[135,166],"effectiveness":[137],"in":[140],"three":[141],"case":[142],"studies,":[143],"i.e.,":[144],"RLAIF,":[147],"Moreover,":[151],"consider":[153],"defenses":[154,168],"including":[155],"known-answer":[156],"detection,":[157,159],"perplexity":[158,161],"windowed":[162],"detection.":[163],"results":[165],"these":[167],"are":[169],"insufficient,":[170],"highlighting":[171],"urgent":[173],"need":[174],"developing":[176],"new":[177],"defense":[178],"strategies.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}