Current Active Speaker Detection (ASD) models have achieved remarkable success, surpassing 90% mAP on the large-scale AVA-ActiveSpeaker benchmark and approaching human-level accuracy. However, our diagnostic analysis reveals that this performance relies on a fragile shortcut: models exhibit a severe "Visual Consistency Bias," prioritizing the association between audio and visual feature consistency over rigorous dynamic temporal synchronization. Consequently, disrupting this visual consistency causes the model to lose track of the active speaker. To exploit this, we propose Context Hiding & Misguidance (CHM), a novel context-aware adversarial attack. Unlike existing methods, CHM strategically manipulates visual feature consistency. Specifically, we design a geometric "Repulsion-Attraction" objective: the Hiding term suppresses the target’s consistent visual features (severing the correct binding), while the Misguidance term steers these features toward the manifold of a silent bystander (creating a false binding). Extensive experiments on the AVA-ActiveSpeaker and UniTalk benchmarks demonstrate the superiority of CHM. Crucially, CHM exhibits remarkable cross-architecture transferability: adversarial perturbations generated on lightweight single-candidate surrogates (e.g., LRASD) successfully compromise sophisticated multi-candidate models like LoCoNet.

Due to the widespread use of 3D objects, they gradually matter in various fields. Selective encryption and secret sharing are common methods to protect 3D objects. However, currently, there is no existing work that integrates these two methods into a unified scheme for 3D objects. This paper proposes a technological scheme tailored for the initial stage of metaverse games, serving as a gateway for players to embark on their game adventure. In this scheme, encryption and secret sharing technologies are harmoniously integrated, not only exploring innovative applications in the realm of 3D object security but also potentially paving the way for future research that bridges the metaverse games and 3D object security domains. Experimental results confirm the feasibility and effectiveness of the proposed scheme, further highlighting its robust adaptability across diverse representations of 3D objects without incurring any additional ciphertext expansion during its processing.

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.

Steganography is a technique for embedding secret messages into digital media while preserving perceptual integrity and avoiding detection. Robust steganography specifically enables secure communication through lossy channels with disturbances, where a critical challenge lies in the receiver's ability to accurately reconstruct hidden messages from corrupted stego data-a process termed error-correction. Recent advancements in stego coding schemes for robust steganography leverage probabilistic decoding to enhance message error-correction accuracy. These schemes employ Maximum-A-Posteriori (MAP) decoders that integrate channel knowledge, i.e. the probability distribution of stego symbols derived from received data, thus necessitating precise estimation of such channel knowledge. While existing approach for Channel Knowledge Estimation (CKE) relies on heuristic, handcrafted methods grounded in empirical assumptions, its effectiveness is limited by the inherent complexity of media content and the diversity of channel disturbance. Besides, it is not compatible with some of the embedding method for robust steganography. To address these limitations, we propose a deep learning-based framework for universal channel knowledge estimation, which significantly improves error-correction performance. Furthermore, we extend this framework to multi-channels robust steganography scenarios, formulating a novel multi-channels knowledge estimation paradigm to enhance message correctness through transmission in multiple channels. Experimental results on various state-of-the-art robust steganography methods demonstrate that our approach outperforms existing CKE methods and coding schemes.

This paper proposes a novel method of vacatingroom-after-encryption reversible data hiding in encrypted image (VRAE RDHEI), which uses the ideas of channel modeling and channel coding to achieve the enhancement of capacity. The framework of the proposed method maps the processes of data embedding and image recovery to a virtual noisy channel for transmitting special flag bits of image content, and then it uses the systematic polar code to ensure error-free transmission for reversible data hiding. On the data hider side, to reversibly vacate room for secret data, the selected bits of the encrypted image are transformed to flag bits and then encoded to fewer parity bits by systematic polar code. On the receiver side, the secret data can be extracted without error and separate from image recovery. To recover the image, the receiver uses pixel prediction to obtain the noisy flag bits and decodes them to the original flag bits by a special channel knowledge-based decoding algorithm with the parity bits. Then, the original image can be recovered by the flag bits. The experimental results prove that the proposed method outperforms the state-of-the-art VRAE methods.

For vacating-room-after-encryption reversible data hiding in encrypted images (VRAE RDHEI), an essential problem is how to address potential errors in data extraction and image recovery. This problem significantly limits the capacities of the existing VRAE RDHEI methods. To solve the problem while losing as little capacity as possible, in this paper, a novel method is proposed that uses the ideas of noisy channel model and channel code. By designing the data hiding mechanism appropriately, the embedding and extraction of data in the proposed method can be equivalent to the input and output of a virtual binary symmetric channel (BSC) model, so that the errors in data extraction are equivalent to the bit transitions in BSC. Based on the virtual BSC model, polar code is used to encode the secret data in the data hider's side. With the help of polar code, the receiver can decode the extracted bits containing errors to obtain correct secret data, then recover the error-free original image based on the corrected secret data. The experimental results proved that, compared with the existing VRAE methods, the proposed method can significantly improve the capacity and the quality of the decrypted images under the premise of complete reversibility.

Robust steganography aims to hide message in cover data with high security and guarantee the success of its message extraction although it is disturbed in transmission channel. In this paper we propose a framework of coding scheme extended from Dual-Syndrome Trellis Codes (Dual-STCs) for robust adaptive steganography. We use the conditional probability distribution of correct stego bits conditioned on disturbed stego data as channel knowledge, and formulate error-correcting as maximizing this probability. By extending Dual-STCs to double-layered embedding, we design an iteratively decoding scheme for error-correcting two layer stego bits from their joint conditional probabilities, and strictly prove its convergence. Besides, we design a method to estimate these probability distributions from stego data pairs uploaded/downloaded from the lossy transmission channel. The channel knowledge can also be used by steganographer, and we propose a universal method to revise steganographic distortion values for higher robustness under the guidance of the channel knowledge. Compared with existing coding methods for robust steganography, our method can make use of channel knowledge to improve error correcting ability and meanwhile maintain high security, which is demonstrated by experimental results.

Current steganalytic classifiers always need a large number of cover-stego image pairs for training. However in this paper we focus on a scenario where steganalysts have a few cover-stego image pairs in hand. Meanwhile steganalysts have no knowledge of the embedding algorithm, and cannot generate corresponding stego images after collecting additional cover images. Hence in this scenario steganalysts cannot match more cover-stego image pairs to augment the training set. To address this issue, we propose a stego feature simulation method to artificially generate cover-stego feature pairs for training. First, we design a cover-stego feature difference model to build the relationship between cover and stego features in pairs. Then, we estimate the model parameters from a few existing cover-stego image pairs in hand. Finally, after extracting steganalytic features from additionally collected cover images, we simulate corresponding stego features with the cover-stego feature difference model to match artificial feature pairs. The experimental results demonstrate that our method can effectively mitigate the shortage of training image pairs by adding adequate artificial feature pairs into training.

JPEG steganalysis aims to detect stego JPEG images. For some robust steganography methods, in order to enhance stego images’ robustness of resisting JPEG recompression from lossy channel such SNS or photo sharing websites, steganographer may intentionally recompress cover image several times with quantization matrix of targeted channel, which thereby make it possible to transmit stego data in such channel for better disguise. In addition, there are huge number of cover JPEG images may be recompressed for various reasons, such as processing by some tools. Thus a better steganalysis method for such images is needed. In this paper, we investigate the steganalysis method for images recompressed with the same quantization matrix, namely, discriminate recompressed JPEG cover images and its stego images. We present some observed phenomenon on recompressed JPEG images, and design methods to enhance the sensitivity of feature based and deep model based steganalysis methods for this task. To verify their effectiveness with different acquisition of recompression prior-knowledge, we conduct experiments in various settings including conventional setting and mixing samples of different recompressing times in training. Their results demonstrate that the proposed method can notably improve detection accuracy on recompressed JPEG images.

In terms of feature-based steganalysis for JPEG images, JPEG phase-aware features (e.g., DCTR and GFR) currently provide the best detection performance on modern adaptive steganographic schemes. But in DCTR and GFR, the types of residual images are relatively single. They only use the convolution residuals obtained with the DCT or Gabor filters of fixed size 8 × 8. In this paper, to further improve DCTR and GFR, two strategies are proposed to enrich the features by diversifying residual images, and the corresponding symmetrization rules for the features are also elaborately designed. First, instead of a single filter size of 8 × 8, convolution filters of multiple sizes are adopted to generate different residual images. Second, we also compute JPEG phase-aware features from the difference images between two convolution residuals. Since the features from convolution residuals and difference images are diverse and complementary, the combination of these two kinds of features can significantly improve the detection accuracy. Last but not least, different symmetrization rules are accordingly designed for these features by considering filter types, filter sizes, and residual subtraction to decrease the feature dimension and enhance the feature robustness. The experimental results demonstrate the effectiveness of our proposed features, and we can further boost the performance by incorporating the knowledge of the selection channel and using the accelerated weighted histogram method.

Moving steganography and steganalysis from the laboratory into the real world, the robustness of steganography needs to be further considered. In this paper, we propose a robust steganographic algorithm to resist the JPEG compression of transport channel based on transport channel matching. Transport channel matching can adjust images to meet the requirements of transport channel so that the impact of JPEG compression from the channel can be reduced. To improve the robustness of steganography, the embedded message bits will be encoded by the error correction code. Then, the adaptive steganographic algorithms will be used to embed messages. To enhance the coding rate, the error correction capability t of the error correction code is dynamically adjusted according to the images. Experimental results on the local simulation of JPEG compression and social network site demonstrate that the proposed steganographic algorithm has a good performance with respect to both robustness and security.

In this paper, we propose to utilize Convolutional Neural Networks (CNNs) and the segmentation-based multi-scale analysis to locate tampered areas in digital images. First, to deal with color input sliding windows of different scales, we adopt a unified CNN architecture. Then, we elaborately design the training procedures of CNNs on sampled training patches. With a set of tampering detectors based on CNNs for different scales, a series of complementary tampering possibility maps can be generated. Last but not least, a segmentation-based method is proposed to fuse these maps and generate the final decision map. By exploiting the benefits of both the small-scale and large-scale analyses, the segmentation-based multi-scale analysis can lead to a performance leap in forgery localization of CNNs. Numerous experiments are conducted to demonstrate the effectiveness and efficiency of our method.

Recently, in order to attack the adaptive steganograhpy more accurately, steganalysis features are associated with the content adaptivity. The adaptive σ version of the steganalysis features incorporates the impact of embedding on the residual to improve the detection. However, this method does not consider whether the embedding impact brings the change on the feature (histogram in the PSRM) which will be utilized by the detectors. Thus, we calculate the expectation of the residual L1distortion under the condition when the corresponding stego and cover residual values are within different quantization intervals, which will be accumulated in the histograms. This adaptive steganalytic scheme, with the relative position of the residual value in the quantization interval, only utilizes the residual distortion that leads to the change on the final feature. The experimental results demonstrate the potential of the proposed idea, especially for small payloads. This idea can also be applied to JPEG phase-aware features.

The GFR (Gabor Filter Residual) features, built as histograms of quantized residuals obtained with 2D Gabor filters, can achieve competitive detection performance against adaptive JPEG steganography. In this paper, an improved version of the GFR is proposed. First, a novel histogram merging method is proposed according to the symmetries between different Gabor filters, thus making the features more compact and robust. Second, a new weighted histogram method is proposed by considering the position of the residual value in a quantization interval, making the features more sensitive to the slight changes in residual values. The experiments are given to demonstrate the effectiveness of our proposed methods.

In this paper, we present a new kind of near-optimal double-layered syndrome-trellis codes (STCs) for spatial domain steganography. The STCs can hide longer message or improve the security with the same-length message comparing to the previous double-layered STCs. In our scheme, according to the theoretical deduction we can more precisely divide the secret payload into two parts which will be embedded in the first layer and the second layer of the cover respectively with binary STCs. When embed the message, we encourage to realize the double-layered embedding by ±1 modifications. But in order to further decrease the modifications and improve the time efficient, we allow few pixels to be modified by ±2. Experiment results demonstrate that while applying this double-layered STCs to the adaptive steganographic algorithms, the embedding modifications become more concentrative and the number decreases, consequently the security of steganography is improved.

This paper focuses on image steganalysis. We use higher order image statistics based on neighborhood information of pixels (NIP) to detect the stego images from original ones. We use subtracting gray values of adjacent pixels to capture neighborhood information, and also make use of “rotation invariant” property to reduce the dimensionality for the whole feature sets. We tested two kinds of NIP feature, the experimental results illustrates that our proposed feature sets are with good performance and even outperform the state-of-art in certain aspect.