Steganalysis models excel on benchmark datasets but struggle in the wild when analyzed images are produced by a processing pipeline unseen during training. This problem known as Cover Source Mismatch (CSM) is particularly hard in realistic settings where practitioners (1) have access to only a small, unlabeled dataset, (2) are unsure of the processing techniques applied to these images, and (3) lack information on the proportion of covers and stegos in that set. To answer this challenge, we introduce TADA (Target Alignment through Data Adaptation), a framework learning to emulate the unknown processing pipeline from a small unlabeled target set. This architecture is trained with a loss combining residual covariance alignment, residual distribution matching, and a ℓ2 loss constraining the emulator to produce realistic images. Across toy and operational targets, TADA yields substantial gains in robustness to CSM and improves operational generalization compared to strong holistic and atomistic baselines. Additional resources are available at this link: https://github.com/RonyAbecidan/TADA.

Traditional inversion algorithms attempt to directly invert the diffusion sampling equation. In this work, built on Latent Diffusion Models (LDMs), we propose a family of algorithms with varying time complexities that perform the search of an antecedent within the latent space and/or the Variational Autoencoder (VAE) decoder.

Many real-life signal-based applications use the Tucker decomposition of a high dimensional/order tensor. A well-known problem with the Tucker model is that its number of entries increases exponentially with its order, a phenomenon known as the “curse of the dimensionality”. The Higher-Order Orthogonal Iteration (HOOI) and Higher-Order Singular Value Decomposition (HOSVD) are known as the gold standard for computing the range span of the factor matrices of a Tucker Decomposition but also suffer from the curse. In this paper, we propose a new methodology with a similar estimation accuracy as the HOSVD with non-exploding computational and storage costs. If the noise-free data follows a Tucker decomposition, the corresponding Tensor Train (TT) decomposition takes a remarkable specific structure. More precisely, we prove that for a$Q$-order Tucker tensor, the corresponding TT decomposition is constituted by$Q-3$3-order TT-core tensors that follow a Constrained Canonical Polyadic Decomposition. Using this new formulation and the coupling property between neighboring TT-cores, we propose a JIRAFE-type scheme for the Tucker decomposition, called TRIDENT. Our numerical simulations show that the proposed method offers a drastically reduced complexity compared to the HOSVD and HOOI while outperforming the Fast Multilinear Projection (FMP) method in terms of estimation accuracy.

The rising popularity of social networks and cloud computing has greatly increased a number of JPEG compressed image exchanges. In this context, the security of the transmission channel and/or the cloud storage can be susceptible to privacy leaks. The selective encryption is an efficient tool to mask the image content and to protect confidentiality while remaining format-compliant. However, image processing in the encrypted domain is not a trivial task. In this paper, we present a JPEG crypto-compression method which allows us to recompress a JPEG crypto-compressed image several times, without any information about the secret key or the original image content. Indeed, using the proposed method in this paper, each recompression can be done directly on the JPEG bitstream by removing the last bit of the code representation of each non-zero coefficient, adapting the entropic code part, and slightly modifying the quantization table. This method is efficient to recompress JPEG crypto-compressed images in terms of compression ratio. Moreover, the decryption of the recompressed image produces an image with a very similar visual quality when compared to the original image, according to the obtained results.

Images that have been altered and more specifically spliced together have invaded the digital domain due to the ease with which we are able to copy and paste them. To detect such forgeries the digital image processing community is proposing new automatic algorithms designed to help human operators reveal manipulated images. In this paper, we focus on a local detection system, which considers which tampered areas produce local statistical effects that do not impact neighboring areas or the image as a whole. We propose to study how the definition of local blocks, considering their size and overlap, impacts final pixel detection. We also propose new features which are an original way to consider the noise of an image as a colored signal. Indeed, in a non-forged image, there is a high correlation of noise between the three color channels R, G and B. We show that an optimal configuration can be defined and in this case the proposed approach outperforms several previously proposed methods using the same tested dataset, in uncompressed and JPEG modes. Note, in this paper we only focus on feature extraction without using machine learning.

For security reasons, more and more digital data are transferred or stored in encrypted domains. In particular for images, selective format-compliant JPEG encryption methods have been proposed for the last ten years. Since encryption is selective, in order to reduce the processing time and to be format-compliant, it is now necessary to evaluate the confidentiality of these selective crypto-compressed JPEG images. It is known that image quality metrics, such as PSNR or SSIM, give a very low correlation with a mean opinion score (MOS) for low quality images. In this paper, we propose an efficient confidentiality metric based on the visual saliency diffusion. We show experimentally that this metric is well correlated with a MOS and efficient to evaluate the confidentiality of selective crypto-compressed JPEG images.

3D meshes are widely used today in very different domains for example; game, medical diagnostic, CAD (computed aided design) or more recently 3-D printing. In this paper, we provide a new data hiding method that has a huge capacity, cp = 3c(n - 1), where n is the vertex number of the mesh and c is an integer. The proposed method consists to compute a Hamiltonian path along the mesh as synchronization. At each step of path building, 3c bits are embedded. The embedding is designed to be a distance relation between a vertex and its father in the path. Moreover, the method uses static arithmetic coding to embed message information. We analyzed the proposed method by inserting RGB images in 3D meshes.

3-D object security is increasingly brought to the attention of the public by the expansion of new multimedia technologies such as the 3-D printing. In the development of crypto-security systems of 3-D objects, we can identify two major directions represented by the cryptography and digital watermarking. A good security system has to be format compliant, has to preserve the original bit rate and, whenever possible, it should be reversible. Watermarking methodology has the advantage of ensuring that the embedded hidden message can be verified at any processing stage such as the transmission, storage and when visualizing the embedding media. In this paper, we review the previous work in 3-D security and analyze the crypto-security of a 3-D watermarking method which embeds information by mesh surface distortion minimization. Then, we discuss future avenues of research by presenting emerging applications.

Efficient data synchronization for 3D mesh models is a new major challenge. 3D models are also now being used to an increasing extent and with current network technology, 3D model compression, visualization and protection demand increases. However, there is still no perfect method to achieve this data synchronization while being blind and robust against various attacks. We propose a blind method based on a Hamiltonian path to synchronize vertex clouds, and particularly on 3D meshes. We experimentally show that it is fast and robust against Gaussian noise. This novel approach can generate better results than mesh-based methods because it does not use vertex connectivity.