Academic Journal
Distribution-Preserving Latent Image Steganography via Conditional Optimal Transport and Theoretical Target Synthesis.
| Τίτλος: | Distribution-Preserving Latent Image Steganography via Conditional Optimal Transport and Theoretical Target Synthesis. |
|---|---|
| Συγγραφείς: | Woźniak, Kamil, Ogiela, Marek R., Ogiela, Lidia |
| Πηγή: | Electronics (2079-9292); Mar2026, Vol. 15 Issue 6, p1321, 22p |
| Θεματικοί όροι: | Bit error rate, JPEG (Image coding standard), Mathematical optimization, Cryptography, Probabilistic generative models |
| Περίληψη: | We propose Distribution-Preserving Latent Steganography via Conditional Optimal Transport (DPL-COT), a coverless image steganography framework for latent diffusion models. Unlike classical cover-modifying schemes, DPL-COT embeds a bitstream directly into the initialization noise latent z T ∼ N (0 , I) without model retraining. Our primary objective is high recoverability and a low bit error rate (BER) under deterministic inversion, which is inherently imperfect due to numerical discretization and VAE nonlinearity. To maximize decoding stability, we restrict embedding to the natural tails of the latent prior by selecting the largest-magnitude coordinates, thereby increasing the sign decision margin against inversion drift. To preserve distributional stealth, per-bit target values are analytically derived from truncated Gaussians matching the marginal distribution of the selected coordinates. Conditional 1D optimal transport is applied independently for each bit class, mapping every coordinate to its target value while preserving rank order. We generate 5000 stego images using a pretrained diffusion model and demonstrate a favorable capacity–reliability trade-off (e.g., 4916 bits/image with 0.473% mean BER) and strong robustness to JPEG compression (sub-1% mean BER at Q = 60 ). Compared with LDStega, a recent LDM-based scheme reporting 99.28% clean-channel accuracy, DPL-COT achieves 99.53% at a comparable operating point and sustains above-99% accuracy under all tested JPEG quality factors. Latent-space tests further confirm negligible cover–stego distribution shift (mean KS 2 < 0.003 , mean W 1 < 0.003 ), a property not formally addressed by prior methods. [ABSTRACT FROM AUTHOR] |
| Copyright of Electronics (2079-9292) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=20799292&ISBN=&volume=15&issue=6&date=20260315&spage=1321&pages=1321-1342&title=Electronics (2079-9292)&atitle=Distribution-Preserving%20Latent%20Image%20Steganography%20via%20Conditional%20Optimal%20Transport%20and%20Theoretical%20Target%20Synthesis.&aulast=Wo%C5%BAniak%2C%20Kamil&id=DOI:10.3390/electronics15061321 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 192631993 RelevancyScore: 1041 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1041.07214355469 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Distribution-Preserving Latent Image Steganography via Conditional Optimal Transport and Theoretical Target Synthesis. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Woźniak%2C+Kamil%22">Woźniak, Kamil</searchLink><br /><searchLink fieldCode="AR" term="%22Ogiela%2C+Marek+R%2E%22">Ogiela, Marek R.</searchLink><br /><searchLink fieldCode="AR" term="%22Ogiela%2C+Lidia%22">Ogiela, Lidia</searchLink> – Name: TitleSource Label: Source Group: Src Data: Electronics (2079-9292); Mar2026, Vol. 15 Issue 6, p1321, 22p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Bit+error+rate%22">Bit error rate</searchLink><br /><searchLink fieldCode="DE" term="%22JPEG+%28Image+coding+standard%29%22">JPEG (Image coding standard)</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Cryptography%22">Cryptography</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilistic+generative+models%22">Probabilistic generative models</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: We propose Distribution-Preserving Latent Steganography via Conditional Optimal Transport (DPL-COT), a coverless image steganography framework for latent diffusion models. Unlike classical cover-modifying schemes, DPL-COT embeds a bitstream directly into the initialization noise latent z T ∼ N (0 , I) without model retraining. Our primary objective is high recoverability and a low bit error rate (BER) under deterministic inversion, which is inherently imperfect due to numerical discretization and VAE nonlinearity. To maximize decoding stability, we restrict embedding to the natural tails of the latent prior by selecting the largest-magnitude coordinates, thereby increasing the sign decision margin against inversion drift. To preserve distributional stealth, per-bit target values are analytically derived from truncated Gaussians matching the marginal distribution of the selected coordinates. Conditional 1D optimal transport is applied independently for each bit class, mapping every coordinate to its target value while preserving rank order. We generate 5000 stego images using a pretrained diffusion model and demonstrate a favorable capacity–reliability trade-off (e.g., 4916 bits/image with 0.473% mean BER) and strong robustness to JPEG compression (sub-1% mean BER at Q = 60 ). Compared with LDStega, a recent LDM-based scheme reporting 99.28% clean-channel accuracy, DPL-COT achieves 99.53% at a comparable operating point and sustains above-99% accuracy under all tested JPEG quality factors. Latent-space tests further confirm negligible cover–stego distribution shift (mean KS 2 < 0.003 , mean W 1 < 0.003 ), a property not formally addressed by prior methods. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Electronics (2079-9292) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=192631993 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/electronics15061321 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 22 StartPage: 1321 Subjects: – SubjectFull: Bit error rate Type: general – SubjectFull: JPEG (Image coding standard) Type: general – SubjectFull: Mathematical optimization Type: general – SubjectFull: Cryptography Type: general – SubjectFull: Probabilistic generative models Type: general Titles: – TitleFull: Distribution-Preserving Latent Image Steganography via Conditional Optimal Transport and Theoretical Target Synthesis. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Woźniak, Kamil – PersonEntity: Name: NameFull: Ogiela, Marek R. – PersonEntity: Name: NameFull: Ogiela, Lidia IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 03 Text: Mar2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20799292 Numbering: – Type: volume Value: 15 – Type: issue Value: 6 Titles: – TitleFull: Electronics (2079-9292) Type: main |
| ResultId | 1 |