{"id":"https://openalex.org/W4402581611","doi":"https://doi.org/10.1109/tvcg.2024.3456150","title":"AdversaFlow: Visual Red Teaming for Large Language Models with Multi-Level Adversarial Flow","display_name":"AdversaFlow: Visual Red Teaming for Large Language Models with Multi-Level Adversarial Flow","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402581611","doi":"https://doi.org/10.1109/tvcg.2024.3456150","pmid":"https://pubmed.ncbi.nlm.nih.gov/39283796"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2024.3456150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3456150","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049050148","display_name":"Dazhen Deng","orcid":"https://orcid.org/0000-0002-9057-8353"},"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":"Dazhen Deng","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-9057-8353","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982517","display_name":"Chuhan Zhang","orcid":"https://orcid.org/0000-0002-2897-3918"},"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":"Chuhan Zhang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031784602","display_name":"Huawei Zheng","orcid":"https://orcid.org/0000-0002-8704-2486"},"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":"Huawei Zheng","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072729601","display_name":"Yuwen Pu","orcid":"https://orcid.org/0000-0003-2311-4943"},"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":"Yuwen Pu","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0003-2311-4943","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058611515","display_name":"Shouling Ji","orcid":"https://orcid.org/0000-0003-4268-372X"},"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":"Shouling Ji","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0003-4268-372X","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073986937","display_name":"Yingcai Wu","orcid":"https://orcid.org/0000-0002-1119-3237"},"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":"Yingcai Wu","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0002-1119-3237","affiliations":[{"raw_affiliation_string":"Zhejiang University, 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":2.6369,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90913112,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"31","issue":"1","first_page":"492","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9837999939918518,"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":0.9837999939918518,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.972599983215332,"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":0.9366000294685364,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.897720456123352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199729919433594},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5656089782714844},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5490260720252991},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.48218050599098206},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.47612816095352173},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43826228380203247},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42861104011535645},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.4234228730201721},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38423794507980347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36803144216537476},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13569077849388123}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.897720456123352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199729919433594},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5656089782714844},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5490260720252991},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.48218050599098206},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.47612816095352173},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43826228380203247},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42861104011535645},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.4234228730201721},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38423794507980347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36803144216537476},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13569077849388123},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2024.3456150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3456150","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:39283796","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39283796","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3558153797","display_name":null,"funder_award_id":"62072400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4278055530","display_name":null,"funder_award_id":"2023YFB3107100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8487668134","display_name":null,"funder_award_id":"U22A2032","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W884650706","https://openalex.org/W2142493242","https://openalex.org/W2343061342","https://openalex.org/W2607223307","https://openalex.org/W2620038827","https://openalex.org/W2752194699","https://openalex.org/W2791826055","https://openalex.org/W2888723145","https://openalex.org/W2891130433","https://openalex.org/W2892051885","https://openalex.org/W2963123635","https://openalex.org/W2965446359","https://openalex.org/W2969221854","https://openalex.org/W2969670093","https://openalex.org/W2969980980","https://openalex.org/W2971173235","https://openalex.org/W2971236179","https://openalex.org/W2973221207","https://openalex.org/W3005984470","https://openalex.org/W3006437051","https://openalex.org/W3023454035","https://openalex.org/W3034069517","https://openalex.org/W3035507081","https://openalex.org/W3091850269","https://openalex.org/W3092273406","https://openalex.org/W3098267758","https://openalex.org/W3108010663","https://openalex.org/W3128529673","https://openalex.org/W3159394994","https://openalex.org/W3164011142","https://openalex.org/W3171850892","https://openalex.org/W3204925778","https://openalex.org/W4281956361","https://openalex.org/W4283170666","https://openalex.org/W4304480495","https://openalex.org/W4310461588","https://openalex.org/W4322707262","https://openalex.org/W4377104732","https://openalex.org/W4384563052","https://openalex.org/W4385305554","https://openalex.org/W4385894687","https://openalex.org/W4387966251","https://openalex.org/W4387966490","https://openalex.org/W4389518965","https://openalex.org/W4390044592","https://openalex.org/W4392169194","https://openalex.org/W4392251767","https://openalex.org/W4394988286","https://openalex.org/W4396833573","https://openalex.org/W4396843791","https://openalex.org/W4397292159","https://openalex.org/W6748184129","https://openalex.org/W6782879696","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6810862904","https://openalex.org/W6853601813","https://openalex.org/W6854515434","https://openalex.org/W6856716710"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W2362367986","https://openalex.org/W348707231","https://openalex.org/W2064719069","https://openalex.org/W3041760129"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"powerful":[5],"but":[6],"also":[7],"raise":[8],"significant":[9],"security":[10,65,128],"concerns,":[11],"particularly":[12],"regarding":[13],"the":[14],"harm":[15],"they":[16],"can":[17,132],"cause,":[18],"such":[19],"as":[20],"generating":[21],"fake":[22],"news":[23],"that":[24],"manipulates":[25],"public":[26],"opinion":[27],"on":[28,46],"social":[29,140],"media":[30,141],"and":[31,50,80,89,100,107,115,122,149,154],"providing":[32],"responses":[33],"to":[34,62,105],"unethical":[35],"activities.":[36],"Traditional":[37],"red":[38,82],"teaming":[39],"approaches":[40],"for":[41,125],"identifying":[42],"AI":[43,127],"vulnerabilities":[44,109],"rely":[45],"manual":[47],"prompt":[48],"construction":[49],"expertise.":[51],"This":[52],"paper":[53],"introduces":[54],"AdversaFlow,":[55],"a":[56,77,81],"novel":[57],"visual":[58],"analytics":[59],"system":[60],"designed":[61],"enhance":[63,133],"LLM":[64,101,134],"against":[66],"adversarial":[67,74,87,98],"attacks":[68],"through":[69],"human-AI":[70],"collaboration.":[71],"AdversaFlow":[72],"involves":[73],"training":[75],"between":[76],"target":[78],"model":[79],"model,":[83],"featuring":[84],"unique":[85],"multi-level":[86],"flow":[88],"fluctuation":[90],"path":[91],"visualizations.":[92],"These":[93],"features":[94],"provide":[95],"insights":[96,124],"into":[97],"dynamics":[99],"robustness,":[102],"enabling":[103,144],"experts":[104],"identify":[106],"mitigate":[108],"effectively.":[110],"We":[111],"present":[112],"quantitative":[113],"evaluations":[114],"case":[116],"studies":[117],"validating":[118],"our":[119],"system's":[120],"utility":[121],"offering":[123],"future":[126],"solutions.":[129],"Our":[130],"method":[131],"security,":[135],"supporting":[136],"downstream":[137],"scenarios":[138],"like":[139],"regulation":[142],"by":[143],"more":[145],"effective":[146],"detection,":[147],"monitoring,":[148],"mitigation":[150],"of":[151],"harmful":[152],"content":[153],"behaviors.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}