{"id":"https://openalex.org/W4416017980","doi":"https://doi.org/10.1145/3746252.3760886","title":"CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors","display_name":"CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017980","doi":"https://doi.org/10.1145/3746252.3760886"},"language":"en","primary_location":{"id":"doi:10.1145/3746252.3760886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760886","pdf_url":null,"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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3760886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120049575","display_name":"Sri Durga Sai Sowmya Kadali","orcid":"https://orcid.org/0009-0007-0212-2967"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sri Durga Sai Sowmya Kadali","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-0212-2967","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054849323","display_name":"Evangelos E. Papalexakis","orcid":"https://orcid.org/0000-0002-3411-8483"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos Papalexakis","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3411-8483","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4857","last_page":"4861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.329800009727478,"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":0.329800009727478,"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":0.21250000596046448,"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/T10028","display_name":"Topic Modeling","score":0.15839999914169312,"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":0.8198999762535095},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4846000075340271},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4099999964237213},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.40310001373291016},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.3993000090122223},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.3257000148296356}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8198999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6080999970436096},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130000114440918},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3760886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760886","pdf_url":null,"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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.02997","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02997","pdf_url":"https://arxiv.org/pdf/2508.02997","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746252.3760886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760886","pdf_url":null,"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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4033307595","display_name":null,"funder_award_id":"W911NF-24-1-0397","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G657183182","display_name":null,"funder_award_id":"IIS 2046086","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"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2469230926","https://openalex.org/W4388850876","https://openalex.org/W4391724817","https://openalex.org/W4396843725","https://openalex.org/W4402669751","https://openalex.org/W4403507961","https://openalex.org/W4404515027","https://openalex.org/W4404783755","https://openalex.org/W4405181600"],"related_works":[],"abstract_inverted_index":{"The":[0],"widespread":[1],"use":[2,52],"of":[3,53,85,95,111,116,131],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"in":[8,15,72],"many":[9],"applications":[10],"marks":[11],"a":[12,66,77,107,121],"significant":[13],"advance":[14],"research":[16],"and":[17,22,50,89,97],"practice.":[18],"However,":[19],"their":[20],"complexity":[21],"hard-to-understand":[23],"nature":[24],"make":[25],"them":[26],"vulnerable":[27],"to":[28,33,151,155],"attacks,":[29],"especially":[30,135],"jailbreaks":[31],"designed":[32],"produce":[34],"harmful":[35],"responses.":[36],"To":[37],"counter":[38],"these":[39],"threats,":[40],"developing":[41],"strong":[42],"detection":[43,59],"methods":[44],"is":[45,120,139,143],"essential":[46],"for":[47,69,91],"the":[48,62,81,92,129,156],"safe":[49],"reliable":[51],"LLMs.":[54],"This":[55,126],"paper":[56],"studies":[57],"this":[58,104],"problem":[60],"using":[61,113],"Contextual":[63,86],"Co-occurrence":[64,87],"Matrix,":[65],"structure":[67],"recognized":[68],"its":[70],"efficacy":[71],"data-scarce":[73],"environments.":[74],"We":[75],"propose":[76],"novel":[78],"method":[79,142],"leveraging":[80],"latent":[82],"space":[83],"characteristics":[84],"Matrices":[88],"Tensors":[90],"effective":[93],"identification":[94],"adversarial":[96],"jailbreak":[98],"prompts.":[99],"Our":[100,141],"evaluations":[101],"show":[102],"that":[103],"approach":[105],"achieves":[106],"notable":[108],"F1":[109],"score":[110],"0.83":[112],"only":[114],"0.5%":[115],"labeled":[117,137],"prompts,":[118],"which":[119],"96.6%":[122],"improvement":[123],"over":[124],"baselines.":[125],"result":[127],"highlights":[128],"strength":[130],"our":[132],"learned":[133],"patterns,":[134],"when":[136],"data":[138],"scarce.":[140],"also":[144],"significantly":[145],"faster,":[146],"speedup":[147],"ranging":[148],"from":[149],"2.3":[150],"128.4":[152],"times":[153],"compared":[154],"baseline":[157],"models.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}