{"id":"https://openalex.org/W7148574670","doi":"https://doi.org/10.48550/arxiv.2604.01083","title":"TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models","display_name":"TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148574670","doi":"https://doi.org/10.48550/arxiv.2604.01083"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01083","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.01083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132795206","display_name":"Awais Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Awais","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132790150","display_name":"Muhammad Umar Farooq","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farooq, Muhammad Umar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132802831","display_name":"Kutub Uddin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uddin, Kutub","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132812946","display_name":"Khalid Malik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malik, Khalid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3644999861717224,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3644999861717224,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.26100000739097595,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.1340000033378601,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/trace","display_name":"TRACE (psycholinguistics)","score":0.8016999959945679},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6477000117301941},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4726000130176544},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4334000051021576},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38100001215934753},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.36640000343322754},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.8016999959945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275000214576721},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5008999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4790000021457672},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4726000130176544},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01083","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.01083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01083","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.5210932493209839,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Partial":[0],"audio":[1,18,97,185],"deepfakes,":[2],"where":[3],"synthesized":[4],"segments":[5],"are":[6,11,23],"spliced":[7],"into":[8],"genuine":[9,61],"recordings,":[10],"particularly":[12],"deceptive":[13],"because":[14],"most":[15,147],"of":[16,104],"the":[17,101,146],"remains":[19],"authentic.":[20],"Existing":[21],"detectors":[22],"supervised:":[24],"they":[25],"require":[26],"frame-level":[27,76],"annotations,":[28],"overfit":[29],"to":[30],"specific":[31],"synthesis":[32],"pipelines,":[33],"and":[34],"must":[35],"be":[36],"retrained":[37],"as":[38],"new":[39],"generative":[40],"models":[41,55,177],"emerge.":[42],"We":[43,50,118],"argue":[44],"that":[45,52,94,124,171],"this":[46],"supervision":[47],"is":[48],"unnecessary.":[49],"hypothesize":[51],"speech":[53,62,106,130,175],"foundation":[54,107,131,176],"implicitly":[56],"encode":[57],"a":[58,91,156],"forensic":[59],"signal:":[60],"forms":[63],"smooth,":[64],"slowly":[65],"varying":[66],"embedding":[67],"trajectories,":[68],"while":[69],"splice":[70],"boundaries":[71],"introduce":[72],"abrupt":[73],"disruptions":[74],"in":[75,174],"transitions.":[77],"Building":[78],"on":[79,121],"this,":[80],"we":[81],"propose":[82],"TRACE":[83,120,135,154],"(Training-free":[84],"Representation-based":[85],"Audio":[86],"Countermeasure":[87],"via":[88],"Embedding":[89],"dynamics),":[90],"training-free":[92,184],"framework":[93],"detects":[95],"partial":[96],"deepfakes":[98],"by":[99],"analyzing":[100],"first-order":[102],"dynamics":[103,173],"frozen":[105],"model":[108],"representations":[109],"without":[110,164],"any":[111,165],"training,":[112],"labeled":[113],"data,":[114],"or":[115],"architectural":[116],"modification.":[117],"evaluate":[119],"four":[122],"benchmarks":[123],"span":[125],"two":[126],"languages":[127],"using":[128],"six":[129],"models.":[132],"In":[133,144],"PartialSpoof,":[134],"achieves":[136],"8.08%":[137],"EER,":[138],"competitive":[139],"with":[140],"fine-tuned":[141],"supervised":[142,157],"baselines.":[143],"LlamaPartialSpoof,":[145],"challenging":[148],"benchmark":[149],"featuring":[150],"LLM-driven":[151],"commercial":[152],"synthesis,":[153],"surpasses":[155],"baseline":[158],"outright":[159],"(24.12%":[160],"vs.":[161],"24.49%":[162],"EER)":[163],"target-domain":[166],"data.":[167],"These":[168],"results":[169],"show":[170],"temporal":[172],"provide":[178],"an":[179],"effective,":[180],"generalize":[181],"signal":[182],"for":[183],"forensics.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-03T00:00:00"}