The manipulation history of Joint Photographic Experts Group (JPEG) compression plays an important role in JPEG image forensics and information hiding. For non-aligned recompressed images, different cropping methods produce non-aligned outputs with varying feature distributions. One such important factor is the shifts of the discrete cosine transform (DCT) grid (i.e., the misalignment parameters) between two compression processes. Although many methods have been proposed to estimate the misalignment parameters, the limited amount of useful information available in small-sized images leads to low accuracy of these methods. To enhance the accuracy of misalignment parameter estimation for small-sized non-aligned images, we propose a novel two-branch network structure that accounts for the unique horizontal and vertical characteristics of non-aligned images. This structure employs convolution to simulate second-order difference (SOD) and incorporates it throughout the training process to optimize the difference parameters dynamically. Based on the insight that cropping operations leave traces in all color channels, we derive the Cg channel through a color space transformation. This approach expands the input dimensionality to four channels (Y, Cb, Cr, and Cg), thereby compensating for the information scarcity in small-sized images. The experimental results show that our method outperforms existing methods on different image sizes, regardless of the known or unknown quality factor (QF) of the first compression. Finally, we propose a re-cropping framework based on the estimated misalignment parameters. The influence of the first cropping is counteracted by a re-cropping operation, which improves the accuracy of existing methods in estimating the first quantization step for non-aligned recompressed images.

The quantization step is a crucial parameter in the JPEG compression process, and provides prior knowledge for JPEG image steganography and forensics. Existing neural network-based methods typically estimate the quantization steps for all discrete cosine transform (DCT) subbands jointly, by treating the entire quantization table as a unified input and leveraging the inter-subband relationships. However, subband relationships vary across different quantization tables, leading to poor generalization for methods that rely heavily on such relationships. To address the above issues, we depart from the strategy that relies on inter-subband relationships and instead train the model on a specific single subband. To compensate for the possible decrease in accuracy due to the lack of relationships between subbands, we extract the ranking features and histogram features from the DCT coefficient histograms of the subbands. Ranking features capture local patterns in DCT histograms by modeling the relative relationships between neighboring coefficients, thereby compensating for the absence of local detail. On the other hand, histogram features represent the overall distribution pattern of the DCT coefficient histograms and capture the global trends and statistical properties in the subbands. We subsequently employ convolutional groups and multilayer perceptron (MLP) structures to extract compression artifacts from these two features. Finally, we introduce a comprehensive evaluation metric, called GenAQt, to quantify the algorithm’s generalization ability across quantization tables. The experimental results demonstrate that our method maintains high accuracy across quantization tables, with RelGenAQt (relative accuracy decrease) exceeding 81% and AbsGenAQt (absolute accuracy decrease) being less than 0.38.

Adversarial examples have been shown to deceive Deep Neural Networks (DNNs), raising widespread concerns about this security threat. More seriously, as different DNN models share critical features, feature-level attacks can generate transferable adversarial examples, thereby deceiving black-box models in real-world scenarios. Nevertheless, we have theoretically discovered the principle behind the limited transferability of existing feature-level attacks: Their attack effectiveness is essentially equivalent to perturbing features in one step along the direction of feature importance in the feature space, despite performing multiple perturbations in the pixel space. This finding indicates that existing feature-level attacks are inefficient in disrupting features through multiple pixel-space perturbations. To address this problem, we propose a P2FA that efficiently perturbs features multiple times. Specifically, we directly shift the perturbed space from pixel to feature space. Then, we perturb the features multiple times rather than just once in the feature space with the guidance of feature importance to enhance the efficiency of disrupting critical shared features. Finally, we invert the perturbed features to the pixels to generate more transferable adversarial examples. Numerous experimental results strongly demonstrate the superior transferability of P2FA over State-Of-The-Art (SOTA) attacks.

Image‐to‐image ( I2I ) translation has emerged as a valuable tool for privacy protection in the digital age, offering effective ways to safeguard portrait rights in cyberspace. In addition, I2I translation is applied in real‐world tasks such as image synthesis, super‐resolution, virtual fitting, and virtual live streaming. Traditional I2I translation models demonstrate strong performance when handling similar datasets. However, when the domain distance between two datasets is large, translation quality may degrade significantly due to notable differences in image shape and edges. To address this issue, we propose Long‐Domain Search GAN ( LDSGAN ), an unsupervised I2I translation network that employs a GAN structure as its backbone, incorporating a novel Real‐Time Routing Search ( RTRS ) module and Sketch Loss. Specifically, RTRS aids in expanding the search space within the target domain, aligning feature projection with images closest to the optimization target. Additionally, Sketch Loss retains human visual similarity during long‐domain distance translation. Experimental results indicate that LDSGAN surpasses existing I2I translation models in both image quality and semantic similarity between input and generated images, as reflected by its mean FID and LPIPS scores of 31.509 and 0.581, respectively.

The quantization step is a crucial parameter in JPEG compression, that can reveal the compression history of a JPEG image. Estimating the quantization steps for single compressed and recompressed images is attracting considerable interest in the field of image forensics and steganalysis. Several effective methods have been proposed, but the performance of these methods still needs to be improved on small-sized and low-quality images. To solve the above problems, feature enrichment is performed on images in the frequency domain, resulting in clustering discrete cosine transform (DCT) coefficients of the same frequency. Then, we construct a hierarchical connection within the residual blocks of the network to represent multi-scale features, enabling the network to learn deep features of the image. At the same time, we use multiple small-sized convolution kernels instead of one large-sized convolution kernel to minimize the impact of block artifacts. Based on the above two ideas, we construct a network model, Res2Net-C, to discover information about the quantization steps in the frequency domain. The integration of multi-channel information of color images is achieved by multi-channel convolution, and the quantization steps of the chrominance and luminance channels of the color images are estimated. The experimental results show that the accuracy of the proposed method for estimating the quantization steps is 29.97% better than that of the existing algorithm with a single compressed dataset and 4.87% better than that of the existing algorithm with a recompressed image dataset. In addition, the method has good performance with mixed datasets that contain both single compressed and recompressed images.