Aug 2026· Frontiers in Medicine· Vol 13· 0 citations· 27 references
TL;DR
Experimental results demonstrate the algorithm’s effectiveness in preserving privacy while enabling perfect image recovery: the container images achieve an average PSNR of 40.08 dB and MSSIM of 0.988 relative to the carriers, confirming near-perceptual-indistinguishability; the reconstructed secret images are recovered with a bit-level accuracy of 100%; and the algorithm maintains robustness under Gaussian noise, salt-and-pepper noise, and PCA compression
Abstract
Steganography plays a critical role in preserving the privacy of medical images by protecting sensitive patient information without compromising image quality or diagnostic utility. This paper proposes a novel lossless privacy protection algorithm for medical images based on pixel displacement. The core innovation lies in the synergistic combination of physical transformation and deep learning—specifically, the integration of shift-rectification with a dual-carrier embedding mechanism. The proposed method begins by applying byte-level pixel shifting to the confidential medical image to generate a shift-rectified version. A deep convolutional neural network is then employed to embed both the original and the rectified medical images into two separate carrier images, ensuring that the resulting container images are visually indistinguishable from the carriers. Subsequently, a dedicated recovery network extracts and reconstructs the lossy shift-rectified image and a degraded version of the original from the two carriers, using the former to calibrate and fully restore the original medical image in a lossless manner. Experimental results demonstrate the algorithm’s effectiveness in preserving privacy while enabling perfect image recovery: the container images achieve an average PSNR of 40.08 dB and MSSIM of 0.988 relative to the carriers, confirming near-perceptual-indistinguishability; the reconstructed secret images are recovered with a bit-level accuracy of 100%; and the algorithm maintains robustness under Gaussian noise, salt-and-pepper noise, and PCA compression with lossless recovery guaranteed. Moreover, the method shows excellent generalization across multiple medical imaging datasets (CT, MRI, and X-ray), highlighting its clinical applicability and innovation in secure medical image transmission systems.
With the rapid development of information technology and network transmission, the generation, storage, and sharing of images are widely applied in daily life. Reversible Data Hiding in Encrypted Images (RDHEI) is a key technology addressing security and privacy challenges. However, existing Vacating Room After Encryption (VRAE) methods for achieving high capacity often rely on MSB prediction, a technique whose performance is inherently tied to image texture. To overcome this, we propose a novel VRAE framework based on interpolation-based difference, creating a stable embedding space via a specialized encryption design. Our methodology uses a unique two-stage encryption process, applying Difference-Preserving Encryption (DPE) to downsampled reference pixels, followed by applying a pseudorandom constant mask (PRF Mask) to non-reference pixels. The core innovation is that the same constant mask is applied to both the original and interpolated images, precisely preserving the difference structure. This enables a "capacityadaptive" embedding strategy that yields bits from zero-difference blocks to secret data, maximizing efficiency. Experimental results confirm that the proposed method achieves a significantly higher embedding capacity on multiple test images compared to existing state-of-the-art schemes. Security analysis confirms the method's robustness against statistical attacks, while complete reversibility is guaranteed.
Cheng-Ta Huang, Zhi-Qi Wang, Hao-Yu Weng et al.· International Conference on...· 0 citations
: The modernization of communication and healthcare environments has introduced critical security challenges, as all transmission is almost certainly done through digital networks prone to attacks. To counteract this, researchers have worked to create methods of data concealment, hiding the existence of sensitive data itself from prying eyes. However, many of these methods lack the necessary ability to balance imperceptibility and payload capacity. In addition, different from generic images, medical images must preserve their structural and visual integrity, requiring frameworks that prioritize maintaining high similarity between images or, at times, complete recovery of the original image. This paper introduces VARStego, a reversible dual-layered steganographic framework designed to conceal confidential patient information within medical images. VARStego uses the Huffman algorithm to compress all patient information in a separate layer of the framework, while a localized variance-based algorithm is employed to analyze medical images to find rough and complex regions. Utilizing these regions, the VARStego embeds data within selected pixels using a redundancy-based algorithm, further improving payload capacity. The proposed VARStego method is tested on the DICOM Library dataset, containing Digital Imaging and Communications in Medicine (DICOM) formatted files and the Kaggle dataset, providing computed tomography (CT) medical images. VARStego achieved a Peak Signal-to-Noise Ratio (PSNR) of 72.192 dB and a perfect Structural Similarity Index Measure of up to 1, ensuring that image quality is maintained. These scores show minimal degradation as the payload size increases from 1 to 50 kilobyte for American Standard Code for Information Interchange (ASCII) payload and 1 to 100 kilobit for bitstring payload, demonstrating the method’s consistent performance.
Basten Andika Salim, Adifa Widyadhani Chanda D'Layla, Ntivuguruzwa Jean de La Croix et al.· Computers, Materials & C...· 0 citations
Spatial domain image steganography has emerged as one of the most widely adopted information-hiding techniques due to its simplicity, high embedding capacity, low computational complexity, and ability to preserve the visual quality of digital images. It plays a significant role in secure communication by concealing confidential information within digital images, thereby protecting sensitive data from unauthorized access in applications such as healthcare, military communication, banking, cloud computing, digital forensics, and multimedia systems. Despite these advantages, spatial domain techniques face several challenges, including vulnerability to steganalysis, limited robustness against image processing operations, and the trade-off between embedding capacity and imperceptibility. This paper presents a comprehensive review of spatial domain image steganography by examining its historical development, fundamental concepts, classification, and major techniques, including Least Significant Bit (LSB), Adaptive LSB, Pixel Value Differencing (PVD), Pixel Indicator Technique (PIT), Optimal Pixel Adjustment Process (OPAP), edge-based methods, and other adaptive spatial approaches. The reviewed techniques are comparatively analyzed based on embedding capacity, imperceptibility, robustness, computational complexity, and practical applicability, and are further illustrated through a quantitative case study that evaluates PSNR, SSIM, and MSE for LSB substitution on a standard test image. The study identifies existing research gaps and highlights future research directions aimed at improving robustness, visual quality, and embedding capacity. By providing a structured and critical synthesis of existing literature, this review serves as a valuable reference for researchers, academicians, and practitioners working in the field of digital image security and information hiding.
Keywords: Least Significant Bit (LSB); Pixel Value Differencing (PVD); Information Hiding; Digital Image Security; Steganalysis
Niranjana K. S., Sidha P. P., A. G et al.· International Journal of Tec...· 0 citations
The integrity and authenticity of digital medical images are paramount for diagnostic accuracy and patient safety. Existing security measures often fail to create a persistent link between the identity of a patient and their medical scans, leaving decrypted data vulnerable. This paper introduces a novel, integrated security frame- work that forges robust and persistent cryptographic link by embedding a patient’s encrypted fingerprint data directly into their medical images. Our end-to-end system synergistically integrates robust biometric processing with a deep learning-based watermarking model. First, a specialized pipeline preprocesses a patient’s fingerprint using binarization, Zhang-Suen thinning, and minutiae extraction. These biometric features are then secured using AES-GCM (Advanced Encryption Standard with Galois/Counter Mode) and a Fuzzy Vault scheme, generating a compact, encrypted payload. Concurrently, the medical image (DICOM) undergoes modality-specific preprocessing to prepare it for embedding. Crucially, the centerpiece of our framework is a jointly trained embedder-extractor neural network that hides this payload with high imperceptibility, ensuring the watermark remains imperceptible to human eyes and designed to be undetectable by diagnostic algorithms, thereby pre- serving the clinical reliability of the scan. Extensive experiments confirm the method’s efficacy, achieving an outstanding mean Peak Signal-to-Noise Ratio (PSNR) of 41.37 dB, a Structural Similarity Index (SSIM) of 0.9804, and a near-perfect Bit Error Rate (BER) of 0.0020 in a no-attack scenario. Furthermore, the framework demonstrates notable resilience against common signal processing attacks, including noise addition and JPEG compression, proving its potential for deployment in secure clinical environments without compromising medical image quality.
Maitri Shekhda, Sakshi Rajani, Rithvik Kashyap Bookinakere Shekar et al.· International Conference on...· 0 citations
Image steganography focuses on hiding hidden information in digital images without degrading the quality of images and avoiding any possibility of detecting the hidden message. Traditional edge-based methods adopt predefined algorithms like Sobel and Canny for detecting the regions suitable for embedding, which may not work efficiently if the images have weak and non-clear edges. Besides, traditional spread spectrum techniques require predefined pseudo-noise (PN) sequences as secret keys, which may pose a threat to security and robustness against any geometric transformations. To address these limitations, This paper proposes a secure image steganography framework that integrates Hybrid Edge-Guided Fourier-Domain Steganography Framework with the Convolutional Neural Network (CNN) based learned detector for securing the process of image steganography. A content adaptive attention mechanism will be adopted to detect the best regions of embedding in the spatial domain, whereas PN classes embedding will be done in the Fourier domain. The CNN based encoder-decoder network will be used to hide and recover the data, and a trained CNN classifier will allow a blind detection. Efficiency and security of this approach will be measured by calculating PSNR, SSIM, MSE, BPP and Re using Xu-Net and Ye-Net steganalysis models.
S. S., Meruvu Sai Kumar· International Journal of Sci...· 0 citations
With the advancement of deep learning-based steganalysis and prevalence of lossy compression mechanisms in social network transmission, traditional steganography based on cover modification (such as LSB substitution) faces dual challenges of security and robustness. This study proposes a novel steganographic framework based on generative artificial intelligence and predefined semantic mapping. Unlike embedding ciphertext in pixel noise, this method utilizes a shared mapping protocol (Codebook) to transform abstract information into concrete visual elements (such as characters, actions, scenes, and styles), and constructs stego-images through generative models. Experimental results show that when both parties share the same key, the system achieves full semantic recovery. Using an explicitly specified pipeline (Gemini 2.5 Flash Image for synthesis and Gemini 2.5 Flash for parsing), we evaluate the scheme on an enlarged, randomly sampled scenario set spanning three to six active semantic dimensions. Across these scenarios, we report per-dimension accuracy, the end-to-end full-recovery rate with 95% confidence intervals, and the partial-recovery rate under controlled JPEG compression, re-scaling, Gaussian noise, and cropping, rather than a single aggregate figure. The results indicate that carrying information at the semantic level yields graceful degradation under common channel distortions together with high visual camouflage, while also revealing that recovery reliability decreases as more semantic dimensions are activated simultaneously. We therefore present these findings as a proof of concept and explicitly separate demonstrated results from hypotheses left to future work. We therefore present these findings as a proof of concept and explicitly separate demonstrated results from hypotheses left to future work.