{"id":"https://openalex.org/W4416233883","doi":"https://doi.org/10.1109/camad67323.2025.11229909","title":"Federated Learning Attack: Fast Image Leakage from Gradients","display_name":"Federated Learning Attack: Fast Image Leakage from Gradients","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4416233883","doi":"https://doi.org/10.1109/camad67323.2025.11229909"},"language":null,"primary_location":{"id":"doi:10.1109/camad67323.2025.11229909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/camad67323.2025.11229909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 30th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Desiree Xavier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Desiree Xavier","raw_affiliation_strings":["Federal University of Pará,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Pará,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056053439","display_name":"Luiz Leite","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luiz Leite","raw_affiliation_strings":["Federal University of Pará,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Pará,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048839201","display_name":"Andr\u00e9 Riker","orcid":"https://orcid.org/0000-0002-6594-8893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Riker","raw_affiliation_strings":["Federal University of Pará,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Pará,Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120402063","display_name":"Eirini Eleni Tsilopoulou","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eirini Eleni Tsilopoulou","raw_affiliation_strings":["Arizona State University,Performance and Resource Optimization in Networks – PROTON Lab, School of Electrical, Computer and Energy Engineering,Tempe,AZ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Performance and Resource Optimization in Networks – PROTON Lab, School of Electrical, Computer and Energy Engineering,Tempe,AZ,USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16458657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6337000131607056,"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":0.6337000131607056,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.299699991941452,"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/T10237","display_name":"Cryptography and Data Security","score":0.007799999788403511,"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/leakage","display_name":"Leakage (economics)","score":0.5171999931335449},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45399999618530273},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43849998712539673},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42820000648498535},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39320001006126404},{"id":"https://openalex.org/keywords/exponential-growth","display_name":"Exponential growth","score":0.3871000111103058},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676000118255615},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/camad67323.2025.11229909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/camad67323.2025.11229909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 30th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2630997112","https://openalex.org/W3091870957","https://openalex.org/W4308691407","https://openalex.org/W4328050303","https://openalex.org/W4384080537","https://openalex.org/W4400887755","https://openalex.org/W4409233071"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,26,30,119,147],"machine":[7,22,46],"learning":[8,23,47],"approach":[9],"able":[10,104],"to":[11,60,105,154],"preserve":[12],"the":[13,34,39,44,55,78,83,87,107,112,125,132,142,156,180],"privacy":[14],"of":[15,43,86,121,130,134,164,170,182],"user\u2019s":[16,52],"data.":[17,53],"Applying":[18],"FL,":[19],"clients":[20],"train":[21],"models":[24],"on":[25,63],"local":[27,79,126],"dataset":[28,80],"and":[29,150,174],"central":[31],"server":[32],"aggregates":[33],"learned":[35],"parameters":[36],"coming":[37],"from":[38,99],"clients.":[40],"The":[41,158],"training":[42,84],"global":[45],"model":[48],"runs":[49],"without":[50],"sharing":[51],"However,":[54],"state-of-the-art":[56],"shows":[57,161],"several":[58],"approaches":[59],"promote":[61],"attacks":[62,72],"FL":[64,127],"systems.":[65],"For":[66],"instance,":[67],"inverting":[68,108],"or":[69],"leaking":[70],"gradient":[71,109],"can":[73],"find,":[74],"with":[75],"high":[76],"precision,":[77],"used":[81],"during":[82],"phase":[85],"FL.":[88],"This":[89],"paper":[90],"presents":[91],"an":[92,135,151,162],"approach,":[93],"called":[94],"FAST":[95],"Improved":[96],"Deep":[97],"Leakage":[98],"Gradients":[100],"(FAST-iDLG),":[101],"which":[102],"is":[103],"improve":[106],"attack,":[110],"considering":[111],"spatial":[113],"correlation":[114],"that":[115],"typically":[116],"exists":[117],"in":[118,124,168],"set":[120],"images":[122,145],"stored":[123],"dataset.":[128],"Instead":[129],"initiating":[131],"attack":[133,171],"image":[136],"using":[137,146],"dummy":[138],"data,":[139],"FAST-iDLG":[140],"blends":[141],"previous":[143],"reconstructed":[144],"sliding":[148],"window":[149],"exponential":[152],"function":[153],"weight":[155],"blend.":[157],"performed":[159],"evaluation":[160],"improvement":[163],"66%":[165],"-":[166,178],"26%":[167],"terms":[169],"success":[172],"rate":[173],"reduces":[175],"by":[176],"55%":[177],"25%":[179],"number":[181],"iterations":[183],"per":[184],"attacked":[185],"image.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-13T00:00:00"}