Recently, image tampering localization techniques for scientific publications have attracted increasing attention due to the prevalence of data manipulation and the integrity issue of image content. However, existing methods are still inefficient to expose tampering traces in scientific images due to their unique properties, such as acquisition noise and ambiguous edges. To address these limitations, we propose a Dynamically Perceived Forgery Conditional Diffusion Model, which formulates the prediction of the localization mask as a noise-state aware denoising process. This process progressively localizes the tampered regions by involving time-step guidance to dynamically perceive tampering traces under the variation of diffusion noise, which is jointly controlled by two conditions, including a forgery condition with hierarchically aggregated forensic clues and an enhanced edge condition with multilevel spatial attention. To conduct dynamic controls efficiently, two conditions are fused and then applied to the denoising process via a channel-cross attention module. Furthermore, in the inference stage, a salient element ensemble-based sampling strategy is developed to further improve the reliability against undesired factors of scientific images. Extensive experiments have been conducted on several scientific image tampering datasets, compared with state-of-the-art methods, which demonstrates our superiority in aspects of intra-/cross-dataset evaluations and robustness against post-processing operations.

Although Federated Learning (FL) enables distributed clients to cooperatively train deep learning models without sharing local data, the iterative FL training process imposes considerable computation and communication overheads on clients. Especially in cloud-edge collaboration situations, heterogeneous and resource-limited edge clients can become a bottleneck for FL. In this paper, we propose FedLTH (Federated Learning with the Lottery Ticket Hypothesis), an FL framework based on the Lottery Ticket Hypothesis and adaptive differential privacy, which aims to improve communication and computing efficiency and privacy security for resource-limited edge clients. First, the pruning rate of each client is set according to their respective resource constraints. The server divides the clients into groups with balanced data distribution and similar pruning rates to ensure the convergence of the global model. Then, a structured model pruning method based on the Lottery Ticket Hypothesis is introduced. Each client group participates in a pruning phase to reduce the computing overhead of clients. Last, an adaptive differential privacy algorithm is designed to preserve client data privacy and improve model accuracy. Through experiments on multiple datasets and non-IID scenarios, we show the effectiveness of FedLTH in privacy preservation and reducing computation and communication overheads.

The rapid evolution of image generation techniques has benefited several fields, but it has also given rise to security concerns. As countermeasures, a series of AI-generated image detection methods have been developed successfully. However, existing methods exhibit an inefficiency in handling the continual emergence of new generative models. To address this issue, we formulate the detection of AI-generated images in an extensible manner using an adapter-based domain incremental learning framework. Specifically, we first investigate the global consistency property of generation artifacts and design a content-agnostic adapter equipped on a vision transformer to extract common forensic features, where a token-level shuffling strategy is constructed for the dual-stream comparison to mitigate the fitting to specific image content. Then, motivated by the compactness of real images and the diversity of fake images due to their inherent generation processes, an asymmetric category-aware domain alignment method is designed to reduce the domain shift arisen from different generators. Finally, a multi-view knowledge distillation module, considering both point-to-point and structure-to-structure forensic knowledge, is devised to alleviate catastrophic forgetting. Experiments are conducted on several protocols using various image generators, and experimental results verify the superiority of our method compared to state-of-the-art methods for extensible detection.

Conventional real-valued 1-D chaotic models are constrained by three fundamental limitations: Restricted chaotic regimes, susceptibility to dynamic degradation in finite-precision implementations, and inherent tradeoffs between security assurance and computational efficiency. These constraints significantly limit the applicability of chaos-based systems. This article presents a novel approach for constructing 1-D discrete complex-variable chaotic systems (1D-DCVCS). The proposed methodology establishes a flexible architecture that enables the derivation of 1D-DCVCS with guaranteed positive Lyapunov exponents. Extensive numerical experiments confirm that the constructed systems exhibit rich dynamical properties, while retaining strong chaotic behavior even in low-precision implementations. Hardware validation via field-programmable gate array implementation confirms the practical viability of the proposed approach. To address existing challenges in chaos-based image encryption (IE), particularly inadequate chaotic behavior, vulnerable key structures, and suboptimal operational efficiency, a lightweight IE scheme is developed by leveraging the advantages of 1D-DCVCS. The cryptographic system achieves enhanced security while maintaining computational efficiency, with quantitative security analysis demonstrating superior performance. This work provides a comprehensive solution that simultaneously addresses theoretical limitations in chaotic system design and practical requirements in secure communication applications.

Deepfake has recently raised severe public concerns about security issues, such as creating fake news of celebrities. As countermeasures, identity-aware detection methods leverage identity information to expose forged videos by measuring identity consistency between the suspicious input and its reference samples. However, the performance of existing methods suffers from notable degradation due to undesired variations of head poses and capturing environments. In this work, we first conduct a statistical analysis to illustrate the influence of different facial regions for forensic purposes, which infers more reliable identity information is located in critical face regions. Motivated by this analysis, we propose a graph learning-based identity-aware deepfake detection framework considering critical contour prior as guidance. First, feature sampling based on contour landmarks is applied to construct the graph data as the input of our critical contour prior-guided graph attention network (CP-GAT), where a node position prediction task is constructed as auxiliary supervision to explore rich relationships between nodes. To enhance pose-invariant ability, a rotation compensation block is integrated into CP-GAT and trained using a pose-calibrated contrastive learning to extract identity features, which takes high-quality front faces as the calibration goal with a progressively updating selection. Besides, an adversarial node masking-based training strategy is proposed as feature augmentation to further enhance the reliability. During the inference stage, the similarity between identity features of the input sample and its reference samples extracted by the trained CP-GAT is used to obtain the detection result. Extensive experiments are conducted on various face forgery datasets and state-of-the-art methods are compared to verify the superiority of the proposed method in terms of detection capability and robustness.

Abstract With the advent of the digital era, millions of facial images are shared online daily, posing severe privacy threats. Generative face anonymization (GFA) methods generate virtual faces to conceal original identities, protecting sensitive information while preserving utility. However, deep learning based user identity linkage (UIL) methods can link similar faces to the same identity and leverage the linked profiles for malicious purposes, including localization and behaviour prediction. These UIL methods pose a significant challenge to the diversity of virtual faces, a challenge that existing GFA methods have not adequately addressed. To address this research gap, we propose Style Diversification‐based Generative Face Anonymization (SD‐GFA), a framework that generates virtual faces with diverse identities and high visual quality. SD‐GFA features an equalized control module to balance input faces and user‐specified keys, a face generation module with a re‐connection strategy for high‐quality synthesis, and a maximum probability simulation module to enhance diversity. Our experiments demonstrate that SD‐GFA effectively mitigates linkage risk by improving the diversity of virtual faces, while also enhancing their utility and visual quality. This study provides a robust solution to enhance the security of anonymized faces shared on the internet.

Face forgery detection receives widespread attention due to the great security threats arising from the development of face forgery technologies. Most existing works define it as a binary classification problem by modeling the spatial and temporal artifacts to distinguish real and fake videos. However, the detector tends to heavily rely on the binary labels and overfit method-specific forgery patterns of the training set, resulting in limited generalization ability. To mitigate this issue, we propose a Temporal Diversified Self-Contrastive Learning (TDSCL) framework, which guides the model to exploit generalized temporal inconsistencies for face forgery detection. Firstly, a Temporally Diversified Transformation (TDT) strategy is designed to create diverse training samples with multiple temporal scales. Subsequently, Short-term Self-contrastive Learning (STSC) and Long-term Self-contrastive Learning (LTSC) are proposed to perform temporal representations of the video at different temporal granularities to capture intrinsic and generalized forensics clues to expose fake videos, which can serve as auxiliary supervisions equipped with different backbones flexibly. Moreover, a Similarity-Guided Adaptive Fusion (SGAF) module is designed to adaptively reinforce the temporal inconsistencies for reliable classification. Extensive experiments verify that the proposed method achieves superior generalization ability over various state-of-the-art methods in different benchmark datasets.

Recently, adversarial perturbations have been used to reassign cost which can enhance the security of steganography, called as adversarial embedding. However, existing methods selected costs to be modified by self-defined rules which were hard to achieve the optimal security against steganalyzers. In this paper, we propose an automatic adversarial embedding scheme called RLAE (deep Reinforcement Learning-based content-adaptive Adversarial Embedding). In RLAE, an agent network utilizes a generative network which generates an embedding policy for cost reassignment automatically according to a basic steganography cost map. Then, an environment network employs a steganalyzer as an attack target that offers rewards for optimizing the agent network. To provide more comprehensive information, we design a joint reward by considering both the adversarial perturbations calculated from the environment network and noise residual signal representing image textures. Experimental results show that the security of the proposed RLAE is superior than state-of-the-art works, especially steganography with for the large payloads.

Recently, the abuse of image generation techniques based on artificial intelligence has posed a great threat to the integrity of digital images. However, existing detection methods are hard to provide generalized detection capability of fake images generated by unseen models. To address this issue, we propose a generalized fake image detection framework based on gated hierarchical multi-task learning, which is supervised by well-designed forensics sub-tasks. Firstly, a global artifact learning task is constructed as binary classification with region masking augmentation. Besides, a block-wise spatial correlation learning task is designed by solving jigsaw puzzle cooperated with color jitter operations, which aims to explore common artifacts of various generators. Finally, a hierarchical multi-task learning paradigm is developed with multi-gate structures, which can adjust the importance of different forensics clues and jointly enhance detection performance. Extensive experiments have been conducted to evaluate the superiority of the proposed method on the open-set scenario with unseen generators

High Efficiency Video Coding (HEVC) places great emphasis on optimizing compression efficiency, where compression efficiency denotes file size ratio before and after compression. The current HEVC steganography is prone to cause degradation in compression efficiency. To analyze and avoid this problem, a Steganographic Compression Efficiency Degradation Model (SCEDM) is first proposed, which leverages the area ratio of different types of Coding Units (CU) as the distribution of block partitioning structure and combines with the K-L divergence to describe the compression efficiency degradation. By minimizing the output of the SCEDM, the degradation of compression efficiency caused by steganographies can be minimized. Besides, it is also proved that this minimizing process will not increase extra visual quality distortion. Based on this model, a novel adaptive steganography using HEVC intra block partitioning structure is proposed. This steganography consists of three parts: the CU Depth based Hierarchical Coding (CDHC) method, the structure merging strategy and the adaptive matching method. The CDHC method can convert secret binary bits to different block structures. The structure merging strategy improves the capacity, and the adaptive matching method minimizes the compression efficiency degradation according to the proposed SCEDM. The proposed steganography is further compared with state-of-the-art steganographies to confirm the effectiveness and advantages of the proposed model and steganography in compression efficiency, capacity, visual quality and resistance to video steganalysis.

This article focuses on designing an event-triggered impulsive fault-tolerant control strategy for the stabilization of memristor-based reaction-diffusion neural networks (RDNNs) with actuator faults. Different from the existing memristor-based RDNNs with fault-free environments, actuator faults are considered here. A hybrid event-triggered and impulsive (HETI) control scheme, which combines the advantages of event-triggered control and impulsive control, is newly proposed. The hybrid control scheme can effectively accommodate the actuator faults, save the limited communication resources, and achieve the desired system performance. Unlike the existing Lyapunov-Krasovskii functionals (LKFs) constructed on sampling intervals or required to be continuous, the introduced LKF here is directly constructed on event-triggered intervals and can be discontinuous. Based on the LKF and the HETI control scheme, new stabilization criteria are derived for memristor-based RDNNs. Finally, numerical simulations are presented to verify the effectiveness of the obtained results and the merits of the HETI control method.

This article focuses on the design of a mode- dependent adaptive event-triggered control (AETC) scheme for the stabilization of Markovian memristor-based reaction-diffusion neural networks (RDNNs). Different from the existing works with completely known transition probabilities, partly unknown transition probabilities (PUTPs) are considered here. The switching conditions and values of memristive connection weights are all correlated with Markovian jumping. A mode-dependent AETC scheme is newly proposed, in which different adaptive event-triggered mechanisms will be applied for different Markovian jumping modes and memristor switching modes. For each given mode, the corresponding event-triggered mechanism can efficiently reduce the number of transmission signals by adaptively adjusting the threshold. Thus, the mode-dependent AETC scheme can effectively save the limited network communication resources for the considered system. Based on the proposed control scheme, a new stabilization criterion is set up for Markovian memristor-based RDNNs with PUTPs. Meanwhile, a memristor-dependent AETC scheme is devised for memristor-based RDNNs. Finally, simulation results are presented to verify the effectiveness and superiority of the analysis results.

In recent years, with the significant improvement of Gener-ative Adversarial Networks (GANs), fake images generated by GAN become hardly distinguishable from real ones, thus threatening the authentication of digital images. To resolve this issue, several fake image detectors based on supervised binary classification have been designed. However, current methods remain vulnerable when testing samples are gener-ated by an unknown GAN model. In this work, an unsuper-vised domain adaptation strategy is introduced to improve the performance in the generalization of GAN-generated image detection by using a small number of unlabeled images from the target domain. Self-Attention block and novel loss function have been constructed to optimize the domain adaptation process, thus getting a better generalization. Experimental results demonstrate that the proposed scheme achieves high detection accuracy with few unlabeled images in the target domain, which shows that unsupervised methods can be used for the detection of GAN-generated images.

Recently, researchers have been dedicated to discovering Generative Adversarial Network (GAN) artifacts and using them to identify generated images. However, current approaches exhibit restricted performance when testing against unseen GAN models, which is also known as the cross-domain scenario. To overcome this limitation, we propose a novel GAN-generated image detection framework by estimating artifact similarity, which is inspired by relation network. The proposed method consists of two stages, including representation learning and representation comparison. For representation learning, ResNet-50 equipped with Instance Normalization in the Shallow layers (ResNet-INS) is constructed as the embedding network to extract generalized features. For representation comparison, Category and Domain-Aware loss function (CDA loss) is designed by leveraging both category and domain information efficiently, which can enlarge inter-class discrepancy of different categories (GAN-generated or pristine images) and improve intra-class compactness from different domains (source attributions) in the same category. Extensive experiments are conducted which consider various cross-domain scenarios to verify the generalization of the proposed method. Besides, our method exhibits satisfying robustness against common post-processings, even when data augmentation is not considered during the training stage.

Cost assignment plays a key role in coding performance and security of video steganography. Existing cost assignment methods (for adaptive video steganography) are designed for specific transform coefficients rather than all transform coefficients. In addition, existing video steganographic frameworks do not allow Syndrome-Trellis Codes (STCs) to modify all transform coefficients in both intra-coded and inter-coded frames at the same time. To address these limitations, in this article, we first propose a novel video steganographic framework. Then, we give a theoretical analysis of distortion drift in both intra- and inter-coding procedures. Based on the analysis, we design a Distortion Drift-Based Cost Assignment method, hereafter referred to as DDCA. DDCA considers the inner-block, inter-block and inter-frame distortion costs in order to improve the coding performance and the security of stego videos when the embedding payload is fixed. We conducted extensive experiments using two video datasets to evaluate the proposed video steganographic framework and DDCA, in terms of the coding performance and the security. Our experiments show that the proposed framework outperforms three recent state-of-the-art methods, for example the coding performance and the security of stego videos can benefit from DDCA by making full use of all nonzero transform coefficients.

This article focuses on the design of fuzzy secure control for a class of coupled systems, which are modeled by a nonlinear$N$-dimensional ($N$-D) parabolic partial differential equation (PDE) subsystem and an ordinary differential equation (ODE) subsystem. Under stochastic deception attacks, a fuzzy secure control scheme is designed, which is effective to tolerate the attacks and ensure the desired performance for the considered systems. A new fuzzy-dependent Poincare–Wirtinger’s inequality (PWI) is proposed. Compared with the traditional Poincare’s inequality, the fuzzy-dependent PWI is more flexible and less conservative. Meanwhile, an augmented Lyapunov–Krasovskii functional (LKF) is newly constructed, which strengthens the correlations of the PDE subsystem and ODE subsystem. Then, on the ground of the fuzzy-dependent PWI and the augmented LKF, new exponential stabilization criteria are set up for the PDE-ODE coupled systems. Finally, a hypersonic rocket car is presented to verify the effectiveness and less conservatism of the obtained results.

This study focuses on the quasisynchronization problem for reaction–diffusion neural networks (RDNNs) in the presence of deception attacks. Under deception attacks, a time–space sampled-data (TSSD) control mechanism is proposed for RDNNs. Compared with traditional control strategies, the proposed control mechanism can not only save network bandwidth but also improve the cybersecurity of communications. Inspired by Halanay’s inequality, a new inequality is proposed, which can be effectively applied to the quasisynchronization problem for dynamical systems. Then, by using this inequality and the Lyapunov functional approach, quasisynchronization criteria are set for RDNNs. The desired control gain is gained from solving a group of linear matrix inequalities. Moreover, in the absence of deception attacks, the exponential synchronization problem is studied for RDNNs. In the end, simulation results are given to demonstrate the usefulness of the theoretical analysis.

Nowadays, verifying the integrity of digital videos is significant especially for applications about multimedia communication. In video forensics, detection of double compression can be treated as the first step to analyze whether a suspicious video undergoes any tampering operations. In the last decade, numerous detection methods have been proposed to address this issue, but most existing methods design a universal detector which is hard to handle various recompression settings efficiently. In this work, we found that the statistics of different Coding Unit (CU) types have dissimilar properties when original videos are recompressed by the increased and decreased bit rates. It motivates us to propose a two-stage cascaded detection scheme for double HEVC compression based on temporal inconsistency to overcome limitations of existing methods. For a given video, CU information maps are extracted from each short-time video clip using our proposed value mapping strategy. In the first detection stage, a compact feature is extracted based on the distribution of different CU types and Kullback–Leibler divergence between temporally adjacent frames. This detection feature is fed into the Support Vector Machine classifier to identify abnormal frames with the increased bit rate. In the second stage, a shallow convolutional neural network equipped with dense connections is designed carefully to learn robust spatiotemporal representations, which can identify abnormal frames with the decreased bit rate whose forensic traces are less detectable. In experiments, the proposed method can achieve more promising detection accuracy compared with several state-of-the-art methods under various coding parameter settings, especially when the original video is recompressed with a low quality (e.g., more than 8%).

Detection of double compression is regarded as one primary step in analyzing the integrity of digital videos, which is of prominent importance in video forensics. However, current methods are vulnerable with the severe lossy quantization in the recompression process such that it is challenging to obtain reliable frame-wise detection results, especially for the high efficiency video coding (HEVC) standard. In view of these issues, in this paper, a hybrid neural network is proposed to reveal abnormal frames in HEVC videos with double compression by learning robust spatio-temporal representations from coding information in the compression domain. Based on the statistical analysis of Coding Units (CUs), it is interesting to find that HEVC video streams contain “rich” coding information that could be leveraged to identify abnormal traces caused by double compression. Two types of coding information maps, including CU Size Map (CSM) and CU Prediction mode Map (CPM), are exploited. In contrast with the conventional paradigm relying on pixel-level representations of decoded frames, CSMs and CPMs of a short-time video clip are treated as the input, aiming to achieve high robustness against recompression of low quality. In our hybrid neural network, an attention-based two-stream residual network is proposed to learn hierarchical representations from CSM and CPM, which are then jointly optimized by the attention-based fusion module. Finally, the temporal variation is modeled by Long Short-Term Memory (LSTM) to obtain frame-wise detection results. We have conducted extensive experiments considering various video content and coding parameters, such as bitrates and sizes of Group of Picture. Experimental results show that our approach can obtain state-of-the-art performance compared with conventional methods, especially when videos are recompressed in the low bitrate coding scenarios.

Bitrate is generally regarded as an important criterion of video quality. However, with sophisticated video editing software, forgers can create fake bitrate videos by up-converting the bitrate of original videos with lower video quality to attract more viewers on video sharing websites. In this work, we first model the generation process of fake bitrate videos and analyze the dominant sources of information loss. It is found that the recompression error generated by the proposed one-step-further recompression operation is an efficient measurement to expose distinguishable quality variation tendencies between true and fake bitrate videos. Based on this analysis, we propose a detection method for fake bitrate videos using a hybrid deep-learning network from recompression error. For an input video, the patch-wise recompression errors are first calculated to increase the learning capability of the network. To learn robust representations of recompression errors in local regions with different degrees of predictability, a hybrid deep-learning network that contains two branches with heterogeneous structures is designed. For noise-like recompression errors, the first branch has a shallow CNN structure initialized with an Inception-like module using multisize convolutional kernels. For zero-element clustered recompression errors, the second branch has a multi-layer perceptron structure equipped with a unique layer that extracts the histogram of zero-element clustered square regions. The output vectors of different branches are concatenated and then jointly optimized to obtain the patch-wise detection results. Finally, the majority voting (local-to-global) strategy is applied to obtain the final detection result. Extensive experiments are conducted to evaluate the detection performance under various coding parameter settings, such as different bitrates, rate-distortion optimization strategies and so on. The experimental results demonstrate the superiority of the proposed method compared with several state-of-the-art methods to provide more fine-grained forensic clues.

The emergence of the high-efficiency video coding (HEVC) standard enables people to enjoy high definition (HD) video content; meanwhile, HD videos, tamper detection has become a crucial issue and gradually aroused people's attention. The detection of double HEVC compressed videos with the same coding parameters is challenging since the recompression traces are inconspicuous. To deal with this issue, a novel method based on the intra prediction mode is proposed in this paper. First, the quality degradation mechanism is analyzed to facilitate the selection of classification features and the source of error in intra coding is fully considered to establish the equivalent error model. Second, the feature model of double HEVC compression detection, which is mainly based on the statistical feature of intra prediction mode, is proposed. Finally, the experiment is carried out in 720p and 1080p HEVC videos instead of low-resolution (CIF or QCIF) videos. Experimental results have demonstrated better efficiency of the proposed method in comparison to the state-of-the-art methods. Besides, the proposed method is more robust to various encoding configurations.

Recently, the success of generating fake images by Generative Adversarial Network (GAN) has threatened the authentication of digital images. To address this issue, several automated fake image detectors have been proposed. However, current methods remain vulnerable when testing samples undergo post-processing attacks. In this work, we employed residual signals of chrominance components from multi color spaces, including YCbCr, HSV and Lab, to learn robust deep representations via the well-designed shallow convolutional neural network (CNN). Then, the learned deep representations from different color spaces are concatenated and then fed into the Random Forest (RF), which is the widely used ensemble classifier, to obtain final detection results. Extensive experiments are conducted on the fake image dataset generated by the advanced GAN technique. Experimental results demonstrate the proposed scheme outperforms state-of-the-art methods and achieves the promising average detection accuracy (above 99%) under several post-processing attacks, such as Gaussian blurring and so on.

In this letter, a deep-learning-based pipeline is proposed to distinguish photographics (PGs) from computer-graphics (CGs) combining convolutional neural network (CNN) and recurrent neural network (RNN). In the preprocessing stage, the color space transformation and the Schmid filter bank are utilized to extract chrominance and luminance components, which suppress the irrelevant information of various image contents for the CG identification task. Then, a dual-path CNN architecture is designed to learn joint feature representations of local patches for exploiting their color and texture characteristics. To extract the global artifact, the directed acyclic graph RNN is applied to model the spatial dependence of local patterns. Finally, the output score of RNN is used to identify the input sample. The CG/PG dataset is constructed by collecting samples from the Internet. Experimental results show that the proposed framework can outperform state-of-the-art methods on identification ability of CGs, especially for images with low resolution.

Detection of double compression with the same coding parameters is a very challenging problem in video forensics, since traces of recompression operations are extremely slight in this case. To solve this problem, we first analyze degradation mechanisms during recompression. It is observed that the video quality tends to become nearly unchanged after multiple recompressions with the same coding parameters. The degree of quality degradation is used to distinguish single and double compressed videos. This property can be described using the convergent tendency of video data to unchanged states after continuous recompressions. For MPEG videos, statistical features of rounding and truncation errors are extracted from the intra-coding process while macroblock-mode based features are obtained from the inter-coding process. The final feature is generated by concatenating these two sets of features to provide robust detection capability. Then, extracted features are fed to the SVM classifier to obtain the final detection result. In addition, aforementioned features are modified and extended to detect double compression on H.264 videos based on the unique coding techniques developed in the H.264 standard, such as intra-prediction. Several public available YUV sequences are used to construct double compression databases with three popular coding standards, including MPEG-2, MPEG-4, and H.264. In experiments, the proposed method outperforms several state-of-the-art methods for different compression qualities and rate control schemes. Experimental results demonstrate the proposed method has more robust detection capability of double compression under various encoding configurations.

In this paper, we propose a novel framework leveraging the advantages of the representational ability of deep learning and domain generalization for face spoofing detection. In particular, the generalized deep feature representation is achieved by taking both spatial and temporal information into consideration, and a 3D convolutional neural network architecture tailored for the spatial-temporal input is proposed. The network is first initialized by training with augmented facial samples based on cross-entropy loss and further enhanced with a specifically designed generalization loss, which coherently serves as the regularization term. The training samples from different domains can seamlessly work together for learning the generalized feature representation by manipulating their feature distribution distances. We evaluate the proposed framework with different experimental setups using various databases. Experimental results indicate that our method can learn more discriminative and generalized information compared with the state-of-the-art methods.

Detecting double MPEG compression is of prime significance in video forensics. However, existing methods are effective only when the primary compression and the secondary compression have different quantiser scales (QS). There is a lack of effective methods dealing with double MPEG compression with the same QS. In this paper, a novel method based on the statistical feature of macroblock mode (MBM) which consists of macroblock type and motion vector in P-frames is proposed to detect double MPEG compression with the same QS. The MBM statistical feature is extracted during multiple decoding procedures when the video is repeatedly compressed with the same QS for several times. Finally, the proposed feature is combined with the support vector machine (SVM) to classify the single MPEG compression and double MPEG compression. Experiments have demonstrated the effectiveness of the proposed method and the robustness to a wide range of QSs and different encoders.