Diffusion-enhanced DCT steganography: reward-guided cover generation for increased embedding capacity with exact lossless-channel recovery

Abstract Discrete cosine transform (DCT)-domain steganography embeds data into quantised DCT coefficients, but its capacity depends on how many cover coefficients are large enough to carry a bit. We propose Diffusion-Enhanced DCT Steganography (DEDS), which fine-tunes a generator to produce covers with more embeddable coefficients. Stable Diffusion v1.5 is fine-tuned with Low-Rank Adaptation, a differentiable DCT reward and an anchor loss. The payload is written by a margin-projected parity embedder whose expected distortion, ( 1/2 +μ)3Q2 / 3, and guaranteed coefficient-domain tolerance, μQ, we derive. On 1,000 prompt- and seed-matched 256 × 256 cover pairs, fine-tuning raised the mean number of eligible coefficients per 8 × 8 block from 1.57 to 16.64 and raw slot capacity from 0.056 to 0.418 bits per pixel (bpp) on the 566 pairs with cover-derived budgets. At 0.30 to 0.60 bpp every message was recovered exactly, with a luminance peak signal-to-noise ratio (PSNR) of 39.9 dB on fine-tuned covers, 6.8 dB above bin-centre embedding and above baseline covers in every payload bin. An optional redundancy mode survived mild JPEG compression and noise at up to 0.02 bpp. Rich-model steganalysis caught the four content-adaptive schemes (area under the curve, AUC, 0.85 to 0.99) and DEDS (AUC 0.997), so the method’s value lies in capacity and fidelity, not security.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-11590881/v1
Primary Topic
Advanced Steganography and Watermarking Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Diffusion-enhanced DCT steganography: reward-guided cover generation for increased embedding capacity with exact lossless-channel recovery

Md. Fahmid-Ul-Alam Juboraj, Muhammad Iqbal Hossain, Mustavi Hassan, Imraj Rabbani et al.
1 links
Research Square
Advanced Steganography and Watermarking Techniques
preprint

Diffusion-enhanced DCT steganography: reward-guided cover generation for increased embedding capacity with exact lossless-channel recovery

Md. Fahmid-Ul-Alam Juboraj, Muhammad Iqbal Hossain, Mustavi Hassan, Imraj Rabbani, MD Ezazul Haque Mahi, Samia Tabassum Chowdhury
preprint en

Abstract

Abstract Discrete cosine transform (DCT)-domain steganography embeds data into quantised DCT coefficients, but its capacity depends on how many cover coefficients are large enough to carry a bit. We propose Diffusion-Enhanced DCT Steganography (DEDS), which fine-tunes a generator to produce covers with more embeddable coefficients. Stable Diffusion v1.5 is fine-tuned with Low-Rank Adaptation, a differentiable DCT reward and an anchor loss. The payload is written by a margin-projected parity embedder whose expected distortion, ( 1/2 +μ)3Q2 / 3, and guaranteed coefficient-domain tolerance, μQ, we derive. On 1,000 prompt- and seed-matched 256 × 256 cover pairs, fine-tuning raised the mean number of eligible coefficients per 8 × 8 block from 1.57 to 16.64 and raw slot capacity from 0.056 to 0.418 bits per pixel (bpp) on the 566 pairs with cover-derived budgets. At 0.30 to 0.60 bpp every message was recovered exactly, with a luminance peak signal-to-noise ratio (PSNR) of 39.9 dB on fine-tuned covers, 6.8 dB above bin-centre embedding and above baseline covers in every payload bin. An optional redundancy mode survived mild JPEG compression and noise at up to 0.02 bpp. Rich-model steganalysis caught the four content-adaptive schemes (area under the curve, AUC, 0.85 to 0.99) and DEDS (AUC 0.997), so the method’s value lies in capacity and fidelity, not security.

Research Square
BRAC University (BD)
Advanced Steganography and Watermarking Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon