Style as Cover: Deep Image Steganography via Stylized Transmission
Authors: Qi Li, Jidong Yang, Huaike Yu, Chunpeng Wang, Suo Gao, Herbert Ho-Ching Iu, Yuantian Miao, Bin Ma, Xiao Chen
Organizations: Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, and Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China · School of Information Science and Engineering, Dalian Polytechnic University, Dalian 116034, China · School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, WA 6009, Australia · School of Computer and Information Sciences, The University of Newcastle, College of Engineering, Science and Environment, Callaghan, NSW 2308, Australia
Image steganography hides secret message within normal images, with most existing works relying on cover-preserving transmission. However, such a paradigm becomes vulnerable once the original cover is exposed or can be reliably approximated. In this paper, we propose StyleStegaNet, a stylized image hiding framework that replaces cover matching with style-concealment transmission. Instead of transmitting a cover-like stego image, StyleStegaNet generates stylized stego images conditioned on publicly available style references, redefining steganography invisibility from cover-preserving concealment to behavior-level camouflage based on style transformation. Such a setting poses a substantial challenge to reliable secret recovery, since neural stylization can significantly alter the feature statistics exploited by deep hiding methods. To address this challenge, StyleStegaNet decouples the overall task into four coordinated stages: stego generation, stylized transmission, structure-preserving reconstruction, and secret recovery. Moreover, StyleStegaNet is optimized with a progressive three-stage training strategy, in which wavelet-domain constraints and perceptual supervision guide the recoverable information toward structural representations. We further provide an analysis showing that secret recoverability is largely restricted to the normalized structural subspace, offering a mechanistic explanation for why directly stylized baselines fail and why a reconstruction-guided recovery path is necessary. Extensive experiments on DIV2K and MS-COCO datasets demonstrate the effectiveness of StyleStegaNet. And few-shot image steganalysis with two deep detectors further shows detection accuracy near random guessing, approximately 51%.
Figures & tables
Figure 1: Comparison with conventional image hiding. StyleStegaNet transmits a recoverable stylized stego image instead of a stego image close to the cover.
Notation
Description
S
Secret image
C
Cover image
Y
Style image
X
Stego image
T
Stylized stego image transmitted by the sender
X′
Recovered stego image
Table 1: Summary of Notation.
Figure 3
Figure 3: StyleStego generation at the sender: a learnable steganographic encoder Eθ followed by a frozen stylization network Fϕ .
Figure 4: Architecture of the RevStego network Rψ and secret decoder Dη .
Stage
Objective
Evaluated pair
PSNR(dB)
Stage 1
LS1
(X,C)
38.63
Stage 2
LS2
(X′,X)
32.78
Stage 3
LS3
(S′,S)
28.49
Table 2: DIV2K training-stage completion PSNR of StyleStegaNet.
Table 3: Stylized-transmission stress test on (S′,S) . Conventional baselines use stego → stylization → original decoder.
Figure 5: Qualitative comparison under stylized transmission. Conventional reveal paths degrade after stylization, while StyleStegaNet remains recoverable.
Method
SiaStegNet
SRNet
Avg.
N=100
Avg.
N=100
StyleStegaNet
51.00
50.75
51.50
51.50
PUSNet
54.65
57.75
62.23
70.50
BalujaNet
65.38
74.50
77.17
81.75
HiDDeN
74.12
93.25
61.83
62.50
HiNet
73.03
94.50
76.42
93.00
Table 4: Deep steganalysis accuracy (%) of the SiaStegNet [ 41 ] and SRNet [ 8 ] detectors. Lower is better; 50% is random guessing.
Figure 6: Few-shot steganalysis accuracy with the SiaStegNet [ 41 ] and SRNet [ 8 ] detectors. The dashed line marks random guessing; lower accuracy indicates lower detectability.
Figure 7: Magnified residual maps under stylized transmission ( 10× ). In this cover-known diagnostic, StyleStegaNet residuals do not visually expose the secret structure; this is not a guarantee against adaptive attacks.
DIV2K: (S′,S)
Methods
PSNR ↑
SSIM ↑
APD ↓
RMSE ↓
Full StyleStegaNet
27.02
0.8830
7.71
12.07
Context refiner
24.91
0.8144
9.90
15.35
w/o secret refinement
23.83
0.7663
11.42
17.29
w/o high-frequency loss
24.86
0.8065
9.96
15.44
Late secret refinement
24.72
0.8056
10.14
15.69
Table 5: Stage 3 ablation on (S′,S) . Arrows indicate the preferred direction.
Image steganalysis, which aims at detecting secret information concealed within images, has become a critical countermeasure for assessing the security of steganography methods, especially the emerging invertible image hiding approaches. However, prior studies merely classify input images into two categories (i.e., stego or cover) and typically conduct steganalysis under the constraint that training and testing data must follow similar distribution, thereby hindering their application in real-world scenarios. To overcome these shortcomings, we propose a novel interpretable image steganalysis framework tailored for invertible image hiding schemes under a challenging zero-shot setting. Specifically, we integrate image hiding, revealing, and steganalysis into a unified framework, endowing the steganalysis component with the capability to recover the secret information embedded in stego images. Additionally, we elaborate a simple yet effective residual augmentation strategy for generating stego images to further enhance the generalizability of the steganalyzer in cross-dataset and cross-architecture scenarios. Extensive experiments on benchmark datasets demonstrate that our proposed approach significantly outperforms the existing steganalysis techniques for invertible image hiding schemes.
Hao Wang, Yiming Yao, Yaguang Xie +2
Zhejiang Provincial Key Laboratory for Sensitive Data Security Protection and Confidentiality Management, Hangzhou Dianzi University, Hangzhou 310018, China · Arcvideo Technology, Hangzhou 310018, China
Image steganography refers to embedding secret messages within cover images while maintaining imperceptibility. Recent advances in deep learning - primarily driven by Convolutional Neural Networks (CNNs) and architectures such as inverse neural networks, autoencoders, and generative adversarial networks - have led to notable progress. However, these frameworks are primarily built on CNN architectures, which treat images as regular grids and are limited by their receptive field size and a bias toward spatial locality. In parallel, Graph Neural Networks (GNNs) have recently demonstrated strong adaptability in several computer vision tasks, achieving state-of-the-art performance with architectures such as Vision GNN (ViG). This work moves in that direction and introduces StegGNN - a novel autoencoder-based, cover-agnostic image steganography framework based on GNNs. By modeling images as graph structures, our approach leverages the representational flexibility of GNNs over the grid-based rigidity of conventional CNNs. We conduct extensive experiments on standard benchmark datasets to evaluate visual quality and imperceptibility. Our results show that our GNN-based method performs comparably to existing CNN benchmarks. These findings suggest that GNNs provide a promising alternative representation for steganographic embedding and open the field of deep learning-based steganography to further exploration of GNN-based architectures.
Despite remarkable progress in steganography, embedding sentence-level information into cover media remains challenging. In this work, we present the concept of Semantic-Payload Steganography, which aims to hide semantically meaningful and structured content, such as sentences, in cover media. Based on this concept, we present Sentence-to-Image Steganography as an instance that enables the hiding of sentence-level messages within a cover image. To accomplish this feat, we propose Semantic-Payload Steganographic Language Model (S2LM), which leverages large language models to embed high-level textual information into images. S2LM redesigns the entire pipeline, involving the LLM throughout the process to enable the hiding and recovery of sentences. To evaluate semantic-payload steganography methods, we establish a benchmark named Invisible Text (IVT), comprising a diverse set of corpus as secret messages. Experimental results demonstrate that S2LM effectively recovers natural-language messages while maintaining high visual quality. The source code will be released at https://github.com/aoli-gei/S2LM.
Huanqi Wu, Huangbiao Xu, Yongliang Xu +3
College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China