{"id":"https://openalex.org/W4391876565","doi":"https://doi.org/10.1162/tacl_a_00639","title":"Red Teaming Language Model Detectors with Language Models","display_name":"Red Teaming Language Model Detectors with Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391876565","doi":"https://doi.org/10.1162/tacl_a_00639"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00639","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00639","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/tacl_a_00639","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022925266","display_name":"Zhouxing Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhouxing Shi","raw_affiliation_strings":["University of California, Los Angeles. zshi@cs.ucla.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles. zshi@cs.ucla.edu","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428931","display_name":"Yihan Wang","orcid":"https://orcid.org/0000-0002-1243-6106"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yihan Wang","raw_affiliation_strings":["University of California, Los Angeles. yihanwang@cs.ucla.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles. yihanwang@cs.ucla.edu","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053347296","display_name":"Fan Yin","orcid":"https://orcid.org/0000-0002-8028-2217"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fan Yin","raw_affiliation_strings":["University of California, Los Angeles. fanyin20@cs.ucla.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles. fanyin20@cs.ucla.edu","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698840","display_name":"Xiangning Chen","orcid":"https://orcid.org/0000-0001-9575-9447"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiangning Chen","raw_affiliation_strings":["University of California, Los Angeles. xiangning@cs.ucla.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles. xiangning@cs.ucla.edu","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California, Los Angeles. kwchang@cs.ucla.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles. kwchang@cs.ucla.edu","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cho-Jui Hsieh","raw_affiliation_strings":["University of California, Los Angeles. chohsieh@cs.ucla.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles. chohsieh@cs.ucla.edu","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010841999","https://openalex.org/A5022925266","https://openalex.org/A5053347296","https://openalex.org/A5087096372","https://openalex.org/A5100428931","https://openalex.org/A5101698840"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":5.8348,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96521353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"174","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8434388637542725},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6119308471679688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5399165153503418},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.47958746552467346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44172123074531555},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07518595457077026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434388637542725},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6119308471679688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5399165153503418},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.47958746552467346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44172123074531555},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07518595457077026}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00639","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00639","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:16ab2f52e76d4170829d7f86547d725a","is_oa":false,"landing_page_url":"https://doaj.org/article/16ab2f52e76d4170829d7f86547d725a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00639","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00639","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1849350726","display_name":"Robust and Generalizable AI Models for Label-free Cellular Organelle Identification","funder_award_id":"2325121","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3812866752","display_name":"CAREER: Robustness Verification and Certified Defense for Machine Learning Models","funder_award_id":"2048280","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5233990263","display_name":"RI: Small: Learning to Optimize: Designing and Improving Optimizers by Machine Learning Algorithms","funder_award_id":"2008173","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G703596469","display_name":"Collaborative Research: SLES: Verifying and Enforcing Safety Constraints in AI-based Sequential Generation","funder_award_id":"2331966","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2799007037","https://openalex.org/W2888482885","https://openalex.org/W2917779306","https://openalex.org/W2949128310","https://openalex.org/W2950681488","https://openalex.org/W2962718684","https://openalex.org/W2963126845","https://openalex.org/W2963341956","https://openalex.org/W2969958763","https://openalex.org/W2982756474","https://openalex.org/W2996851481","https://openalex.org/W3035183289","https://openalex.org/W3099729825","https://openalex.org/W3101449015","https://openalex.org/W3103491646","https://openalex.org/W3104423855","https://openalex.org/W3155332104","https://openalex.org/W3170572542","https://openalex.org/W3173343821","https://openalex.org/W3203534993","https://openalex.org/W4224308101","https://openalex.org/W4285225959","https://openalex.org/W4288089799","https://openalex.org/W4299567010","https://openalex.org/W4318351452","https://openalex.org/W4322718191","https://openalex.org/W4323650348","https://openalex.org/W4353007481","https://openalex.org/W4360891421","https://openalex.org/W4364387756","https://openalex.org/W4385573699","https://openalex.org/W4385894687","https://openalex.org/W6757615711","https://openalex.org/W6761551260","https://openalex.org/W6763240421","https://openalex.org/W6767101625","https://openalex.org/W6769627184","https://openalex.org/W6776811381","https://openalex.org/W6787335730","https://openalex.org/W6801783160","https://openalex.org/W6810081322","https://openalex.org/W6846556436","https://openalex.org/W6848955896","https://openalex.org/W6849393593","https://openalex.org/W6850625674","https://openalex.org/W6850824531","https://openalex.org/W6851071894","https://openalex.org/W6851601001","https://openalex.org/W6851663954"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2366906938","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"prevalence":[2],"and":[3,14,39,49],"strong":[4],"capability":[5],"of":[6,28,51,62,91,140,157],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"present":[11],"significant":[12],"safety":[13],"ethical":[15],"risks":[16],"if":[17],"exploited":[18],"by":[19,128],"malicious":[20],"users.":[21],"To":[22],"prevent":[23],"the":[24,47,77,88,92,104,108,121,138,144,150,155],"potentially":[25],"deceptive":[26],"usage":[27],"LLMs,":[29],"recent":[30],"work":[31],"has":[32],"proposed":[33],"algorithms":[34],"to":[35,86,102,153],"detect":[36],"LLM-generated":[37,158],"text":[38,159],"protect":[40],"LLMs.":[41],"In":[42,94],"this":[43],"paper,":[44],"we":[45,97,115],"investigate":[46],"robustness":[48,156],"reliability":[50],"these":[52],"LLM":[53,101,123],"detectors":[54,142],"under":[55],"adversarial":[56],"attacks.":[57],"We":[58],"study":[59,145],"two":[60],"types":[61],"attack":[63],"strategies:":[64],"1)":[65],"replacing":[66],"certain":[67],"words":[68],"in":[69,143],"an":[70,83,99],"LLM\u2019s":[71],"output":[72],"with":[73,146],"their":[74],"synonyms":[75],"given":[76],"context;":[78],"2)":[79],"automatically":[80],"searching":[81],"for":[82],"instructional":[84,109],"prompt":[85],"alter":[87],"writing":[89],"style":[90],"generation.":[93],"both":[95],"strategies,":[96],"leverage":[98],"auxiliary":[100,122],"generate":[103],"word":[105],"replacements":[106],"or":[107],"prompt.":[110],"Different":[111],"from":[112],"previous":[113],"works,":[114],"consider":[116],"a":[117,129],"challenging":[118],"setting":[119],"where":[120],"can":[124],"also":[125],"be":[126],"protected":[127],"detector.":[130],"Experiments":[131],"reveal":[132],"that":[133],"our":[134],"attacks":[135],"effectively":[136],"compromise":[137],"performance":[139],"all":[141],"plausible":[147],"generations,":[148],"underscoring":[149],"urgent":[151],"need":[152],"improve":[154],"detection":[160],"systems.":[161],"Code":[162],"is":[163],"available":[164],"at":[165],"https://github.com/shizhouxing/LLM-Detector-Robustness.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}