Identity-preserving models have led to notable progress in generating personalized content. Unfortunately, such models also exacerbate risks when misused, for instance, by generating threatening content targeting specific individuals. This paper introduces the Attribute Misbinding Attack, a novel method that poses a threat to identity-preserving models by inducing them to produce Not-Safe-For-Work (NSFW) content. The attack's core idea involves crafting benign-looking textual prompts to circumvent text-filter safeguards and leverage a key model vulnerability: flawed attribute binding that stems from its internal attention bias. This results in misattributing harmful descriptions to a target identity and generating NSFW outputs. To facilitate the study of this attack, we present the Misbinding Prompt evaluation set, which examines the content generation risks of current state-of-the-art identity-preserving models across four risk dimensions: pornography, violence, discrimination, and illegality. Additionally, we introduce the Attribute Binding Safety Score (ABSS), a metric for concurrently assessing both content fidelity and safety compliance. Experimental results show that our Misbinding Prompt evaluation set achieves a 5.28 % higher success rate in bypassing five leading text filters (including GPT-4o) compared to existing main-stream evaluation sets, while also demonstrating the highest proportion of NSFW content generation. The proposed ABSS metric enables a more comprehensive evaluation of identity-preserving models by concurrently assessing both content fidelity and safety compliance.

Diffusion models have made significant strides in visual content generation but also raised increasing demands on generated image detection. Existing detection methods have achieved considerable progress, but they usually suffer a significant decline in accuracy when detecting images generated by an unseen diffusion model. In this paper, we seek to address the generalizability of generated image detectors from the perspective of hard sample classification. The basic idea is that if a classifier can distinguish generated images that closely resemble real ones, then it can also effectively detect less similar samples, potentially even those produced by a different diffusion model. Based on this idea, we propose Diffusion Reconstruction Contrastive Learning (DRCT), a universal framework to enhance the generalizability of the existing detectors. DRCT generates hard samples by high-quality diffusion reconstruction and adopts contrastive training to guide the learning of diffusion artifacts. In addition, we have built a million-scale dataset, DRCT-2M, including 16 types diffusion models for the evaluation of generalizability of detection methods. Extensive experimental results show that detectors enhanced with DRCT achieve over a 10% accuracy improvement in cross-set tests. The code, models, and dataset will soon be available at https://github.com/beibuwandeluori/DRCT.

JPEG-domain enhancement improves the visual quality of JPEG images by directly manipulating the decoded DCT (discrete cosine transform) coefficients, which inevitably leads to mixed compression and enhancement artifacts. Existing forensic methods that merely consider JPEG artifacts are unsuitable to address such mixed artifacts and hence suffer a considerable performance decline in compression parameter estimation and lack the ability to estimate the enhancement parameter. This work attempts to explore the characterization of the mixed artifacts, and to further estimate both the enhancement and compression parameters of JPEG-domain enhanced images. First, a statistical likelihood function is proposed to characterize the periodicity of DCT coefficients, which can measure how well an enhanced image is de-enhanced back to its JPEG compressed version given the compression and enhancement parameters. The proposed likelihood function reaches its maximum if the parameters match their true values. Then, a forensic method of enhancement detection and parameter estimation is developed based on the proposed likelihood function for two kinds of classical JPEG-domain enhancement. Specifically, JPEG-domain enhanced images are detected by thresholding a scalar feature computed upon the likelihoods, and the enhancement and compression parameters are estimated by locating the maximal likelihood. In addition, mathematical proof of the de-enhancement feasibility is provided. Experimental results demonstrate that the proposed method outperforms the compared methods in both enhancement detection and parameter estimation.

Quantization plays a pivotal role in JPEG compression with respect to the tradeoff between image fidelity and storage size, and the blind estimation of quantization parameters has attracted considerable interest in the fields of image steganalysis and forensics. Existing estimation methods have made great progress, but they usually suffer a sharp decline in accuracy when addressing small-size JPEG decompressed bitmaps due to the insufficiency of coefficients. Aiming to alleviate this issue, this paper proposes a generic clustering-based framework to improve the performance of the existing methods. The core idea is to gather as many coefficients as possible by clustering subbands before feeding them into a step estimator. The proposed framework is implemented using hierarchical clustering with two kinds of histogram-like features. Extensive experiments are conducted to validate the effectiveness of the proposed framework on a variety of images of different sizes and quality factors, and the results show that notable improvements can be achieved. In addition to quantization step estimation, we believe the idea behind the proposed framework might provide inspiration for other forensic tasks to alleviate their performance issues induced by sample insufficiency.

Visual secret sharing (VSS) is a new technique for sharing a binary image into multiple shadows. For VSS, the original image can be reconstructed from the shadows in any qualified set, but cannot be reconstructed from those in any forbidden set. In most traditional VSS schemes, the shadows held by participants have the same importance. However, in practice, a certain number of shadows are given a higher importance due to the privileges of their owners. In this article, a novel ( t , s , k , n )-threshold VSS scheme is proposed based on access structure partition. First, we construct the basis matrix of the proposed ( t , s , k , n )-threshold VSS scheme by utilizing a new access structure partition method and sub-access structure merging method. Then, the secret image is shared by the basis matrix as n shadows, which are divided into s essential shadows and n - s non-essential shadows. To reconstruct the secret image, k or more shadows should be collected, which include at least t essential shadows; otherwise, no information about the secret image can be obtained. Compared with related schemes, our scheme achieves a smaller shadow size and a higher visual quality of the reconstructed image. Theoretical analysis and experiments indicate the effectiveness of the proposed scheme.

The local variance of image intensity is a typical measure of image smoothness. It has been extensively used, for example, to measure the visual saliency or to adjust the filtering strength in image processing and analysis. However, to the best of our knowledge, no analytical work has been reported about the effect of JPEG compression on image local variance. In this paper, a theoretical analysis on the variation of local variance caused by JPEG compression is presented. First, the expectation of intensity variance of 8×8 non-overlapping blocks in a JPEG image is derived. The expectation is determined by the Laplacian parameters of the discrete cosine transform coefficient distributions of the original image and the quantization step sizes used in the JPEG compression. Second, some interesting properties that describe the behavior of the local variance under different degrees of JPEG compression are discussed. Finally, both the simulation and the experiments are performed to verify our derivation and discussion. The theoretical analysis presented in this paper provides some new insights into the behavior of local variance under JPEG compression. Moreover, it has the potential to be used in some areas of image processing and analysis, such as image enhancement, image quality assessment, and image filtering.

Unsharp masking (USM) sharpening is a basic technique for image manipulation and editing. In recent years, the detection of USM sharpening has attracted attention from image forensics point of view. After USM sharpening, overshoot artifacts, which shape image texture, are generated along image edges. By utilizing the special characteristic of the texture modification caused by the USM sharpening, a novel method called edge perpendicular binary coding is proposed in this letter to detect USM sharpening. Extensive experiments have been conducted to show the superiority of the proposed method over the existing methods.

Detection of double JPEG compression plays an important role in digital image forensics. Some successful approaches have been proposed to detect double JPEG compression when the primary and secondary compressions have different quantization matrices. However, detecting double JPEG compression with the same quantization matrix is still a challenging problem. In this paper, an effective error-based statistical feature extraction scheme is presented to solve this problem. First, a given JPEG file is decompressed to form a reconstructed image. An error image is obtained by computing the differences between the inverse discrete cosine transform coefficients and pixel values in the reconstructed image. Two classes of blocks in the error image, namely, rounding error block and truncation error block, are analyzed. Then, a set of features is proposed to characterize the statistical differences of the error blocks between single and double JPEG compressions. Finally, the support vector machine classifier is employed to identify whether a given JPEG image is doubly compressed or not. Experimental results on three image databases with various quality factors have demonstrated that the proposed method can significantly outperform the state-of-the-art method.

Fragility is one of the most important properties of authentication-oriented image hashing. However, to date, there has been little theoretical analysis on the fragility of image hashing. In this paper, we propose a measure called expected discriminability for the fragility of image hashing and study this fragility theoretically based on the proposed measure. According to our analysis, when Gray code is applied into the discrete-binary conversion stage of image hashing, the value of the expected discriminability, which is dominated by the quantization stage of image hashing, is no more than 1/2. We further evaluate the expected discriminability of the image-hashing scheme that uses adaptive quantization, which is the most popular quantization scheme in the field of image hashing. Our evaluation reveals that if deterministic adaptive quantization is applied, then the expected discriminability of the image-hashing scheme can reach the maximum value (i.e., 1/2). Finally, some experiments are conducted to validate our theoretical analysis and to compare the performance of several quantization schemes for image hashing.

How to measure the security of image hashing is still an open issue in the field of image authentication. Some works have been conducted on the security measure of image hashing. One of the most important works is the randomness measure proposed by Swaminathan, which uses differential entropy as a metric to evaluate the security of randomized image features and has been applied mainly in the security analysis of the feature extraction stage of image hashing. It is meaningful to measure the randomness of the image features over the secret-key set for the security of image hashing because the image features extracted by image hashing should be generated randomly and difficult to guess. However, as is well known, differential entropy is not invariant to scaling; thus it might not be enough to evaluate the security of randomized image features. In this paper, we show the fact that if the image features of an image hash function are scaled by a constant that is large than one, then the tradeoff between the robustness and the fragility of the image hash function will not change at all, but the security indicated by the randomness measure will increase. The above-mentioned fact seems to contradict the following. First, the security of image hashing, which conflicts with robustness and fragility, cannot increase freely. Secondly, a deterministic operation, such as deterministic scaling, does not change the security of image hashing in terms of the difficulty of guessing the secret key or randomized image features. Therefore, the randomness measure should be modified to be invariant to scaling at least.