{"id":"https://openalex.org/W7125507597","doi":"https://doi.org/10.48550/arxiv.2601.16027","title":"Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment","display_name":"Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125507597","doi":"https://doi.org/10.48550/arxiv.2601.16027"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.16027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.16027","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.16027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123718545","display_name":"Yiran Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123717047","display_name":"Xiang Ao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ao, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123712042","display_name":"Jing Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123707209","display_name":"Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005667980","display_name":"Qiwei Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Qiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123681205","display_name":"Qing He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Qing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.14659999310970306,"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":0.14659999310970306,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.12080000340938568,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.10329999774694443,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/live-streaming","display_name":"Live streaming","score":0.4864000082015991},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.4577000141143799},{"id":"https://openalex.org/keywords/d\u00e9j\u00e0-vu","display_name":"D\u00e9j\u00e0 vu","score":0.4422999918460846},{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.42910000681877136},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37220001220703125},{"id":"https://openalex.org/keywords/risk-model","display_name":"Risk model","score":0.32760000228881836},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.28780001401901245}],"concepts":[{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.5677000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5382000207901001},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.515500009059906},{"id":"https://openalex.org/C2776741261","wikidata":"https://www.wikidata.org/wiki/Q3027665","display_name":"Live streaming","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C81366925","wikidata":"https://www.wikidata.org/wiki/Q158103","display_name":"D\u00e9j\u00e0 vu","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.34279999136924744},{"id":"https://openalex.org/C2986432223","wikidata":"https://www.wikidata.org/wiki/Q5449740","display_name":"Risk model","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C3017634809","wikidata":"https://www.wikidata.org/wiki/Q84862664","display_name":"Risk communication","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2984870255","wikidata":"https://www.wikidata.org/wiki/Q5196451","display_name":"User engagement","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.16027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.16027","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.16027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.16027","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,132],"live":[3,55,146],"streaming":[4,56],"has":[5],"transformed":[6],"online":[7,126],"interaction,":[8],"enabling":[9],"massive":[10],"real-time":[11,115],"engagement":[12],"but":[13],"also":[14],"exposing":[15],"platforms":[16],"to":[17,91,101],"complex":[18],"risks":[19,29],"such":[20],"as":[21],"scams":[22],"and":[23,38,86,111],"coordinated":[24],"malicious":[25],"behaviors.":[26],"Detecting":[27],"these":[28],"is":[30],"challenging":[31],"because":[32],"harmful":[33],"actions":[34],"often":[35],"accumulate":[36],"gradually":[37],"recur":[39],"across":[40,105],"seemingly":[41],"unrelated":[42],"streams.":[43],"To":[44],"address":[45],"this,":[46],"we":[47],"propose":[48],"CS-VAR":[49,135],"(Cross-Session":[50],"Evidence-Aware":[51],"Retrieval-Augmented":[52],"Detector)":[53],"for":[54,114,145],"risk":[57,68,109],"assessment.":[58],"In":[59],"CS-VAR,":[60],"a":[61,74],"lightweight,":[62],"domain-specific":[63],"model":[64,100],"performs":[65],"fast":[66],"session-level":[67],"inference,":[69],"guided":[70],"during":[71],"training":[72],"by":[73],"Large":[75],"Language":[76],"Model":[77],"(LLM)":[78],"that":[79,140],"reasons":[80],"over":[81],"retrieved":[82],"cross-session":[83],"behavioral":[84],"evidence":[85],"transfers":[87],"its":[88],"local-to-global":[89],"insights":[90],"the":[92,98,129],"small":[93,99],"model.":[94],"This":[95],"design":[96],"enables":[97],"recognize":[102],"recurring":[103],"patterns":[104],"streams,":[106],"perform":[107],"structured":[108],"assessment,":[110],"maintain":[112],"efficiency":[113],"deployment.":[116],"Extensive":[117],"offline":[118],"experiments":[119],"on":[120],"large-scale":[121],"industrial":[122],"datasets,":[123],"combined":[124],"with":[125],"validation,":[127],"demonstrate":[128],"state-of-the-art":[130],"performance":[131],"CS-VAR.":[133],"Furthermore,":[134],"provides":[136],"interpretable,":[137],"localized":[138],"signals":[139],"effectively":[141],"empower":[142],"real-world":[143],"moderation":[144],"streaming.":[147]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-01-24T00:00:00"}