{"id":"https://openalex.org/W7166644226","doi":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","title":"DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation","display_name":"DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7166644226","doi":"https://doi.org/10.1109/cyber-ai70573.2026.11755132"},"language":"en","primary_location":{"id":"doi:10.1109/cyber-ai70573.2026.11755132","doi":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","pdf_url":null,"source":{"id":"https://openalex.org/S7407105982","display_name":"International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053427562","display_name":"Yuting Xin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuting Xin","raw_affiliation_strings":["University of Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120841702","display_name":"Hanyu Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanyu Cai","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Binqi Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binqi Shen","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129518387","display_name":"Lier Jin","orcid":null,"observed_orcids":[]},"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":"Lier Jin","raw_affiliation_strings":["Fuqua School of Business, Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuqua School of Business, Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139672652","display_name":"Lan Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Hu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4343,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96032436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","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/T10883","display_name":"Ethics and Social Impacts of AI","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/concept-drift-detection","display_name":"concept drift detection","score":0.7480000257492065},{"id":"https://openalex.org/keywords/adaptive-model-updating","display_name":"adaptive model updating","score":0.703000009059906},{"id":"https://openalex.org/keywords/model-uncertainty","display_name":"model uncertainty","score":0.8299999833106995},{"id":"https://openalex.org/keywords/hate-speech-detection","display_name":"hate speech detection","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5976999998092651},{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468999743461609},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C2910001868","wikidata":"https://www.wikidata.org/wiki/Q458","display_name":"European union","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cyber-ai70573.2026.11755132","doi":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","pdf_url":null,"source":{"id":"https://openalex.org/S7407105982","display_name":"International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.28725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28725","pdf_url":"https://arxiv.org/pdf/2606.28725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2606.28725","doi":"https://doi.org/10.48550/arxiv.2606.28725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28725","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1109/cyber-ai70573.2026.11755132","doi":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/cyber-ai70573.2026.11755132","pdf_url":null,"source":{"id":"https://openalex.org/S7407105982","display_name":"International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.428600013256073}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166644226.pdf","grobid_xml":"https://content.openalex.org/works/W7166644226.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2099419573","https://openalex.org/W2341497066","https://openalex.org/W2920807444","https://openalex.org/W2947838315","https://openalex.org/W2949678053","https://openalex.org/W2963351448","https://openalex.org/W3032574806","https://openalex.org/W3115453555","https://openalex.org/W3120042896","https://openalex.org/W3128611684","https://openalex.org/W3172559340","https://openalex.org/W4220851938","https://openalex.org/W4320024160","https://openalex.org/W4385573017","https://openalex.org/W4385893817","https://openalex.org/W4386366369","https://openalex.org/W4393138529","https://openalex.org/W4398250170","https://openalex.org/W4409378386","https://openalex.org/W4410061981","https://openalex.org/W4412082472","https://openalex.org/W4412887767","https://openalex.org/W4413409554","https://openalex.org/W4413413021","https://openalex.org/W4415316358","https://openalex.org/W4416434703","https://openalex.org/W4416955425","https://openalex.org/W4417080477","https://openalex.org/W6941281238","https://openalex.org/W7130600670","https://openalex.org/W7130686082","https://openalex.org/W7135230844","https://openalex.org/W7140122471","https://openalex.org/W7154615764","https://openalex.org/W7155070693","https://openalex.org/W7161271111","https://openalex.org/W7162472079","https://openalex.org/W7162654644","https://openalex.org/W7163198642","https://openalex.org/W7164884348","https://openalex.org/W7168183441","https://openalex.org/W7213907176"],"related_works":["https://openalex.org/W7138317614","https://openalex.org/W7134208366","https://openalex.org/W4416008939","https://openalex.org/W4405713884","https://openalex.org/W4416156405","https://openalex.org/W7223017469","https://openalex.org/W7216030070","https://openalex.org/W7212411357","https://openalex.org/W4382318835","https://openalex.org/W7168383996"],"abstract_inverted_index":{"Automated":[0],"toxicity":[1,197],"moderation":[2,57],"systems":[3],"operate":[4],"in":[5,42],"dynamic":[6],"online":[7],"environments":[8],"where":[9],"harmful":[10],"behavior":[11],"evolves":[12],"through":[13],"coded":[14],"language,":[15],"shifting":[16],"targets,":[17],"and":[18,80,107,117,137,141,155,176],"strategic":[19],"adaptation":[20,95,133],"to":[21,150,158],"enforcement.":[22],"Existing":[23],"drift":[24,62,130,186],"detection":[25,63,187],"methods":[26],"often":[27],"focus":[28],"on":[29,112,152,160],"global":[30,71,129],"distributional":[31],"change,":[32],"but":[33],"such":[34],"signals":[35],"may":[36],"miss":[37],"safety-relevant":[38,84],"shifts":[39],"that":[40,59,97,122],"emerge":[41],"localized":[43],"harm":[44],"subspaces":[45],"or":[46],"high-risk":[47,103],"model-error":[48],"regions.":[49],"This":[50],"paper":[51],"introduces":[52],"DriftGuard,":[53],"a":[54,93],"safety-aware":[55,123,185],"adaptive":[56,196],"framework":[58,69],"combines":[60],"multi-monitor":[61],"with":[64,170,188],"selective":[65],"model":[66,76,89,191],"updating.":[67],"The":[68],"tracks":[70],"text":[72],"drift,":[73,75,79],"identity-harm":[74],"uncertainty,":[77],"toxic-risk":[78],"false-negative-risk":[81],"drift.":[82],"When":[83],"change":[85],"is":[86,90],"detected,":[87],"the":[88],"updated":[91],"using":[92],"hard-mix":[94],"set":[96],"prioritizes":[98],"likely":[99],"false":[100],"negatives,":[101],"identity-related":[102],"examples,":[104,106],"false-positive-risk":[105],"uncertain":[108],"boundary":[109],"cases.":[110],"Experiments":[111],"Civil":[113,153],"Comments":[114,154],"temporal":[115],"shift":[116,120],"Jigsaw-to-DynaHate":[118],"cross-dataset":[119],"show":[121],"monitors":[124],"detect":[125],"risks":[126],"missed":[127],"by":[128,174,180],"alone.":[131],"Hard-mix":[132],"improves":[134],"toxic":[135,146,171],"recall":[136,147,172],"accuracy":[138],"over":[139],"no-update":[140],"random-balanced":[142],"baselines.":[143],"It":[144],"raises":[145],"from":[148,156],"0.8453":[149],"0.8777":[151],"0.7107":[157],"0.8523":[159],"DynaHate.":[161],"Bootstrap":[162],"analysis":[163],"further":[164],"shows":[165],"stable":[166],"DynaHate":[167],"safety":[168],"gains,":[169],"increasing":[173],"0.1418":[175],"false-negative":[177],"prevalence":[178],"decreasing":[179],"0.0781.":[181],"Overall,":[182],"DriftGuard":[183],"links":[184],"targeted,":[189],"lightweight":[190],"updating":[192],"for":[193],"more":[194],"robust":[195],"moderation.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-07-01T00:00:00"}
