{"id":"https://openalex.org/W7172000463","doi":"https://doi.org/10.48550/arxiv.2607.27811","title":"SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark Attack","display_name":"SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark Attack","publication_year":2026,"publication_date":"2026-07-30","ids":{"openalex":"https://openalex.org/W7172000463","doi":"https://doi.org/10.48550/arxiv.2607.27811"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.27811","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27811","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.2607.27811","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144127009","display_name":"Chunpeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chunpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144114873","display_name":"Yanan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yanan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144100994","display_name":"Zhiqiu Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Zhiqiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144094301","display_name":"Jidong Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138715477","display_name":"Suo Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Suo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5144096197","display_name":"Qi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qi","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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.8583999872207642,"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":0.8583999872207642,"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":0.0478999987244606,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.026599999517202377,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.9348000288009644},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.7741000056266785},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5206999778747559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5020999908447266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.45089998841285706}],"concepts":[{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.9348000288009644},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7741000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7232000231742859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952999830245972},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6179999709129333},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.45089998841285706},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3939000070095062},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2777000069618225},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.27811","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27811","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.2607.27811","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27811","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4860749840736389}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"watermark":[1,25,53,67,122,147,168,195],"attacks":[2],"typically":[3],"rely":[4],"on":[5,176],"predefined":[6],"signal-processing":[7],"operations":[8],"or":[9],"locally":[10],"constrained":[11],"restoration":[12],"networks,":[13],"making":[14],"it":[15],"difficult":[16],"to":[17,60,78,135],"capture":[18,115],"the":[19,62,116,145],"long-range":[20,117],"dependencies":[21,118],"of":[22,65,119],"globally":[23,120],"distributed":[24,121],"signals":[26],"and":[27,36,47,69,143,163,182,198],"resulting":[28],"in":[29],"an":[30],"unfavorable":[31],"trade-off":[32,193],"between":[33,194],"removal":[34],"effectiveness":[35,197],"visual":[37],"fidelity.":[38,200],"In":[39,149],"this":[40],"paper,":[41],"we":[42],"propose":[43],"SPFM-Net,":[44],"a":[45,72,124,155,191],"semantic-prior-guided":[46],"frequency-constrained":[48],"Mamba":[49],"framework":[50],"for":[51],"invisible":[52,66],"attack.":[54],"SPFM-Net":[55,151,189],"first":[56],"employs":[57],"high-ratio":[58],"masking":[59],"disrupt":[61],"spatial":[63],"coherence":[64],"signals,":[68,123],"then":[70],"utilizes":[71],"partially":[73],"fine-tuned":[74],"pretrained":[75],"Masked":[76],"Autoencoder":[77],"reconstruct":[79],"semantically":[80],"consistent":[81],"image":[82,141],"from":[83,110,139],"sparse":[84],"observations":[85],"while":[86,106,170],"suppressing":[87,108],"watermark-related":[88,99,137],"information.":[89],"A":[90],"Multi-scale":[91],"Residual":[92],"Frequency":[93],"Feature":[94,129],"Interaction":[95],"module":[96],"subsequently":[97],"aggregates":[98],"residual":[100],"features":[101,138],"across":[102],"multiple":[103],"receptive":[104],"fields,":[105],"adaptively":[107],"responses":[109],"watermark-irrelevant":[111],"regions.":[112],"To":[113],"further":[114],"lightweight":[125],"Mamba-based":[126],"Global":[127],"State-space":[128],"Modeling":[130],"(GSFM)":[131],"unit":[132],"is":[133,152],"introduced":[134],"separate":[136],"natural":[140],"content":[142],"suppress":[144],"remaining":[146],"traces.":[148],"addition,":[150],"optimized":[153],"using":[154],"multi-level":[156],"objective":[157],"that":[158,188],"jointly":[159],"imposes":[160],"spatial-,":[161],"frequency-,":[162],"edge-domain":[164],"constraints,":[165],"enabling":[166],"effective":[167],"suppression":[169],"preserving":[171],"perceptual":[172,199],"quality.":[173],"Extensive":[174],"experiments":[175],"representative":[177],"spatial-domain,":[178],"transform-domain,":[179],"orthogonal":[180],"moment-based,":[181],"deep":[183],"learning-based":[184],"watermarking":[185],"schemes":[186],"demonstrate":[187],"achieves":[190],"favorable":[192],"attack":[196]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}