{"id":"https://openalex.org/W7160544200","doi":"https://doi.org/10.48550/arxiv.2605.04405","title":"Detecting Deepfakes via Hamiltonian Dynamics","display_name":"Detecting Deepfakes via Hamiltonian Dynamics","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160544200","doi":"https://doi.org/10.48550/arxiv.2605.04405"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04405","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04405","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.04405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135561585","display_name":"Harry Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Harry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135550076","display_name":"Ming-Hui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ming-Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135623066","display_name":"Tianyi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135627435","display_name":"Weili Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Weili","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135573590","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Liqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135601130","display_name":"Mohan Kankanhalli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kankanhalli, Mohan","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8744000196456909,"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":0.8744000196456909,"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":0.0868000015616417,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.011900000274181366,"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/generative-grammar","display_name":"Generative grammar","score":0.5242000222206116},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.4643000066280365},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4415000081062317},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4377000033855438},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4207000136375427},{"id":"https://openalex.org/keywords/dissipative-system","display_name":"Dissipative system","score":0.4153999984264374},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4147999882698059},{"id":"https://openalex.org/keywords/hamiltonian","display_name":"Hamiltonian (control theory)","score":0.39489999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5339999794960022},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952999949455261},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4207000136375427},{"id":"https://openalex.org/C99692599","wikidata":"https://www.wikidata.org/wiki/Q596577","display_name":"Dissipative system","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C130787639","wikidata":"https://www.wikidata.org/wiki/Q5645293","display_name":"Hamiltonian (control theory)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36660000681877136},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3034000098705292},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C121770821","wikidata":"https://www.wikidata.org/wiki/Q2072471","display_name":"Hamiltonian system","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C50429861","wikidata":"https://www.wikidata.org/wiki/Q3554830","display_name":"Stable manifold","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C143218062","wikidata":"https://www.wikidata.org/wiki/Q722799","display_name":"Principle of least action","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04405","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04405","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.04405","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04405","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":"Preprint"},"sustainable_development_goals":[{"score":0.6665862202644348,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Driven":[0],"by":[1,49],"the":[2,117],"rapid":[3],"development":[4],"of":[5,59],"generative":[6,72],"AI":[7],"models,":[8],"deepfake":[9,33],"detectors":[10],"are":[11,131,141],"compelled":[12],"to":[13,17,40,64,78,96,133,144],"undergo":[14],"periodic":[15],"recalibration":[16],"capture":[18],"newly":[19],"developed":[20],"synthetic":[21],"artifacts.":[22],"To":[23,101],"break":[24],"this":[25,127],"cycle,":[26],"we":[27,52,104],"propose":[28],"a":[29,122,155,208],"new":[30],"perspective":[31],"on":[32,202],"detection:":[34],"moving":[35],"from":[36,162],"static":[37],"pattern":[38],"recognition":[39],"dynamical":[41],"stability":[42,156,210],"analysis.":[43],"Specifically,":[44],"our":[45],"approach":[46],"is":[47],"motivated":[48],"physics-inspired":[50,209],"priors:":[51],"hypothesize":[53],"that":[54,196],"natural":[55],"images,":[56],"as":[57,89,121,154],"products":[58],"dissipative":[60],"physical":[61],"processes,":[62],"tend":[63],"settle":[65],"near":[66,165],"stable,":[67],"low-energy":[68,136],"equilibria.":[69],"In":[70],"contrast,":[71],"models":[73],"optimize":[74],"for":[75,212],"statistical":[76],"similarity":[77],"real":[79,129],"images":[80,130,140],"but":[81],"do":[82],"not":[83],"explicitly":[84],"enforce":[85],"structural":[86],"constraints":[87],"such":[88],"geometric":[90],"smoothness,":[91],"leaving":[92],"deepfakes":[93],"more":[94,142],"likely":[95,143],"occupy":[97],"unstable,":[98],"high-energy":[99],"states.":[100],"operationalize":[102],"this,":[103],"introduce":[105],"Hamiltonian":[106,188],"Action":[107],"Anomaly":[108],"Detection":[109],"(HAAD),":[110],"comprising":[111],"three":[112],"contributions:":[113],"\\textbf{i)}":[114],"We":[115,150,178],"model":[116],"image":[118],"latent":[119,160],"manifold":[120],"potential":[123],"energy":[124,191],"surface.":[125],"Under":[126],"hypothesis,":[128],"expected":[132],"produce":[134,173],"basin-like":[135],"responses,":[137],"whereas":[138],"fake":[139],"induce":[145],"high-potential,":[146],"high-gradient":[147,171],"responses.":[148,176],"\\textbf{ii)}":[149],"employ":[151],"Hamiltonian-inspired":[152],"dynamics":[153],"probe.":[157],"By":[158],"releasing":[159],"states":[161],"rest,":[163],"samples":[164,172],"stable":[166],"regions":[167],"remain":[168],"bounded,":[169],"while":[170],"larger":[174],"trajectory":[175,185],"\\textbf{iii)}":[177],"quantify":[179],"these":[180],"dynamic":[181],"behaviors":[182],"through":[183],"two":[184],"statistics,":[186],"\\ie,":[187],"action":[189],"and":[190],"dissipation.":[192],"Extensive":[193],"experiments":[194],"show":[195],"HAAD":[197],"outperforms":[198],"evaluated":[199],"state-of-the-art":[200],"baselines":[201],"challenging":[203],"cross-dataset":[204],"transfer":[205],"benchmarks,":[206],"supporting":[207],"prior":[211],"digital":[213],"forensics.":[214]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}