{"id":"https://openalex.org/W7162676255","doi":"https://doi.org/10.48550/arxiv.2605.28298","title":"REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis","display_name":"REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162676255","doi":"https://doi.org/10.48550/arxiv.2605.28298"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28298","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.2605.28298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066784099","display_name":"\u96f7\u82e5\u5bd2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Ruohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134387878","display_name":"Jianxin Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jianxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137231800","display_name":"Wanli Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Wanli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137260009","display_name":"Huimin Pei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Huimin","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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.3009999990463257,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.3009999990463257,"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/T11644","display_name":"Spam and Phishing Detection","score":0.1762000024318695,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.10570000112056732,"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/steganalysis","display_name":"Steganalysis","score":0.9438999891281128},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6182000041007996},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5547000169754028},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5206000208854675},{"id":"https://openalex.org/keywords/steganography","display_name":"Steganography","score":0.4855000078678131},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45879998803138733}],"concepts":[{"id":"https://openalex.org/C107368093","wikidata":"https://www.wikidata.org/wiki/Q448176","display_name":"Steganalysis","level":4,"score":0.9438999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384999752044678},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5547000169754028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.550000011920929},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C108801101","wikidata":"https://www.wikidata.org/wiki/Q15032","display_name":"Steganography","level":3,"score":0.4855000078678131},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3887999951839447},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29429998993873596}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28298","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.2605.28298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28298","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8647768497467041}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,53],"real-world":[1],"scenarios":[2],"of":[3,143],"linguistic":[4,65],"steganalysis,":[5],"tested":[6],"texts":[7],"usually":[8],"come":[9],"from":[10,103],"unseen":[11],"domains":[12],"with":[13,127],"different":[14],"vocabularies,":[15],"topics,":[16],"writing":[17],"styles,":[18],"and":[19,76,81,86,106],"steganographic":[20],"generation":[21],"patterns,":[22],"which":[23],"can":[24,35,134],"significantly":[25],"degrade":[26],"the":[27,47,68,78,87,128,131],"detection":[28,48,138],"performance.":[29],"Although":[30],"existing":[31],"cross-domain":[32,64,137],"steganalysis":[33],"methods":[34],"effectively":[36],"alleviate":[37],"this":[38,54],"problem":[39],"through":[40],"distribution":[41],"alignment,":[42],"domain-invariant":[43],"feature":[44,79],"learning,":[45],"etc.,":[46],"performance":[49],"is":[50,70],"not":[51],"satisfactory.":[52],"paper,":[55],"we":[56,98,112],"propose":[57],"a":[58,100,114],"post-training":[59],"representation":[60],"editing":[61],"method":[62,133],"for":[63],"steganalysis.":[66],"Specifically,":[67],"detector":[69],"first":[71],"trained":[72],"on":[73],"source-domain":[74,115,154],"data,":[75],"then":[77],"extractor":[80],"classifier":[82],"are":[83,90],"kept":[84],"frozen,":[85],"intermediate":[88],"representations":[89],"deterministically":[91],"edited":[92],"before":[93],"classification.":[94],"For":[95,109],"domain":[96,110],"adaptation,":[97],"construct":[99],"domain-offset":[101],"vector":[102],"marginal":[104],"source":[105],"target":[107],"representations.":[108],"generalization,":[111],"derive":[113],"cover-to-stego":[116],"direction":[117],"to":[118],"guide":[119],"sample-specific":[120],"editing.":[121],"Experimental":[122],"results":[123],"show":[124],"that":[125],"compared":[126],"advanced":[129],"methods,":[130],"proposed":[132],"achieve":[135],"high":[136],"performance,":[139],"especially":[140],"in":[141],"terms":[142],"F1-score,":[144],"while":[145],"requiring":[146],"no":[147],"architecture":[148],"modification":[149],"or":[150],"parameter":[151],"updates":[152],"after":[153],"training.":[155]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-29T00:00:00"}