Voice conversion refers to transforming the speaker of a voice into a target speaker while keeping the content unchanged. Current solutions either rely on feature representations from large-scale pre-trained models or require complex model designs and intensive training, lacking exploration of intrinsic speech features. This restricts the exploration of lightweight and robust methods. In this study, we remove pre-trained models and depart from complex mutual information minimization for feature decoupling. Instead, we revisit decoupling methods based on instance normalization. To address it, we introduce a novel feature coupling module named cross-adaptive instance normalization (CAIN), which extends the adaptive instance normalization (AdaIN). Beyond offering style injection capabilities, CAIN is designed to maintain content consistency by reconstructing frame-level statistics in mel-spectrograms. The results indicate that CAIN, serving as a lightweight plugin, significantly improves conventional instance normalization-driven approaches. Building upon this, we propose RLVC, which achieves robust performance with a mere 5.29M parameters.

Facial dubbing has attracted growing research interests due to its creative and practical applications. An ideal facial dubbing video should exhibit accurate lip-sync and high visual quality. However, prior methods fall short in fully exploring the relationship between two pairs of critical elements: distinguishing mouth shape and texture for accurate lip-sync performance; aligning the driving audio and high-frequency details for better visual quality. To address these challenges, we propose a progressive framework ProDub for this task. Specifically, we propose an audio-supervised contrastive approach to disentangle the mouth shape and texture, along with a novel lip-shape-aware loss as a constraint for producing accurate lip-sync. For high-quality visual output, a lip-aware temporal-enhanced network is designed to improve the lip details while ensuring temporal coherency based on a learned prior. Extensive experiments demonstrate that our ProDub improves lip-sync by 10.7% and visual quality by 28.5% compared to state-of-the-art methods .1

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video content and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this article, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and interframe inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces from a global perspective, respectively. The two components are designed using a novel long-distance attention mechanism. One component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves state-of-the-art performance, and the proposed long-distance attention method can effectively capture pivotal parts for face forgery.

Abstract Because the JPEG recompression in social networks changes the DCT coefficients of uploaded images, applying image steganography in popular image-sharing social networks requires robustness. Currently, most robust steganography algorithms rely on the resistance of embedding to the general JPEG recompression process. The operations in a specific compression channel are usually ignored, which reduces the robustness performance. Besides, to acquire the robust cover image, the state-of-the-art robust steganography needs to upload the cover image to social networks several times, which may be insecure regarding behavior security. In this paper, a robust steganography method based on the softmax outputs of a trained classifier and protocol message embedding is proposed. In the proposed method, a deep learning-based robustness classifier is trained to model the specific process of the JPEG recompression channel. The prediction result of the classifier is used to select the robust DCT blocks to form the embedding domain. The selection information is embedded as the protocol messages into the middle-frequency coefficients of DCT blocks. To further improve the recovery possibility of the protocol message, a robustness enhancement method is proposed. It decreases the predicted non-robust possibility of the robustness classifier by modifying low-frequency coefficients of DCT blocks. The experimental results show that the proposed method has better robustness performance compared with state-of-the-art robust steganography and does not have the disadvantage regarding behavior security. The method is universal and can be implemented in different JPEG compression channels after fine-tuning the classifier. Moreover, it has better security performance compared with the state-of-the-art method when embedding large-sized secret messages.

In this paper, we propose a new DeepFakes forensics approach called forensic symmetry, which determines whether two symmetrical face patches contain the same or different natural features. To do this, we propose a multi-stream learning structure composed of two feature extractors. The first feature extractor obtains symmetry feature from the front face images. The second feature extractor obtains similarity feature from the side face images. Symmetry feature and similarity feature are collectively called natural feature. Forensic symmetry system maps the pair of symmetrical face patches into the angular hyperspace to quantify the difference of their natural features. The greater the difference of natural features, the higher the tamper probability of face images. The heuristic prediction algorithm is designed to compute the tamper probability of DeepFakes at video level. A series of experiments are carried out to evaluate the effectiveness of our proposed forensic symmetry system. Experimental results show that our approach is effective for DeepFakes detection under the scenarios of homologous detection, heterogeneous detection, and re- compression detection.

Deep neural networks (DNNs) are vulnerable to adversarial attacks which can fool the classifiers by adding small perturbations to the original example. The added perturbations in most existing attacks are mainly determined by the gradient of the loss function with respect to the current example. In this paper, a new average gradient-based adversarial attack is proposed. In our proposed method, via utilizing the gradient of each iteration in the past, a dynamic set of adversarial examples is constructed first in each iteration. Then, according to the gradient of the loss function with respect to all the examples in the constructed dynamic set and the current adversarial example, the average gradient can be calculated, which is used to determine the added perturbations. Different from the existing adversarial attacks, the proposed average gradient-based attack optimizes the added perturbations through a dynamic set of adversarial examples, where the size of the dynamic set increases with the number of iterations. Our proposed method possesses good extensibility and can be integrated into most existing gradient-based attacks. Extensive experiments demonstrate that, compared with the state-of-the-art gradient-based adversarial attacks, the proposed attack can achieve higher attack success rates and exhibit better transferability, which is helpful to evaluate the robustness of the network and the effectiveness of the defense method.

Deep Neural Networks based video frame interpolation, synthesizing in-between frames given two consecutive neighboring frames, typically depends on heavy model architectures, preventing them from being deployed on small terminals. When directly adopting the lightweight network architecture from these models, the synthesized frames may suffer from poor visual appearance. In this paper, a lightweight-driven video frame interpolation network (L2BEC2) is proposed. Concretely, we first improve the visual appearance by introducing the bidirectional encoding structure with channel attention cascade to better characterize the motion information; then we further adopt the local network lightweight idea into the aforementioned structure to significantly eliminate its redundant parts of the model parameters. As a result, our L2BEC2performs favorably at the cost of only one third of the parameters compared with the state-of-the-art methods on public datasets. Our source code is available at https://github.com/Pumpkin123709/LBEC.git.

Since recent advances in speech synthesis techniques, it is important to develop robust speech anti-spoofing systems against all major spoofing attacks. In this paper, we propose a novel spoofing speech detection model by jointing ResNeXt with neighbor filters (NF-ResNeXt) to improve the robustness of speech anti-spoofing models. Inspired by higher-order cepstral coefficients are more difficult to be maintained during the speech synthesis procedure, we present a novel neighbor filter module for extracting the residual features to enhance the robustness of cepstral features. Then, we introduce a neural network architecture based on ResNeXt model for processing the residual features and calculating the scores of speech clips being spoofed. The NF-ResNeXt model is trained on the training set of ASVspoof 2019 logical access (LA) dataset and achieves an equal error rate (EER) of 5.13% on the evaluation dataset, which outperforms the existing state-of-the-art speech anti-spoofing models.

The abuse of DeepFake technique has raised enormous public concerns in recent years. Currently, the existing DeepFake datasets suffer some weaknesses of obvious visual artifacts, minimal Asian proportion, backward synthesis methods and short video length. To make up these weaknesses, we have constructed an Asian large-scale challenging DeepFake dataset to enable the training of DeepFake detection models and organized the accompanying video track of the first Fake Media Forensics Challenge of China Society of Image and Graphics (FMFCC-V). The FMFCC-V dataset is by far the first and the largest public available Asian dataset for DeepFake detection, which contains 38102 DeepFake videos and 44290 pristine videos, corresponding more than 23 million frames. The source videos in the FMFCC-V dataset are carefully collected from 83 paid individuals and all of them are Asians. The DeepFake videos are generated by four of the most popular face swapping methods. Extensive perturbations are applied to obtain a more challenging benchmark of higher diversity. The FMFCC-V dataset can lend powerful support to the development of more effective DeepFake detection methods. We contribute a comprehensive evaluation of six representative DeepFake detection methods to demonstrate the level of challenge posed by FMFCC-V dataset. Meanwhile, we provide a detailed analysis of the top submissions from the FMFCC-V competition.

Abstract Most social media channels are lossy where videos are transcoded to reduce transmission bandwidth or storage space, such as social networking sites and video sharing platforms. Video transcoding makes most video steganographic schemes unusable for hidden communication based on social media. This paper proposes robust video steganography against video transcoding to construct reliable hidden communication on social media channels. A new strategy based on principal component analysis is provided to select robust embedding regions. Besides, side information is generated to label these selected regions. Side information compression is designed to reduce the transmission bandwidth cost. Then, one luminance component and one chrominance component are joined to embed secret messages and side information, notifying the receiver of correct extraction positions. Video preprocessing is conducted to improve the applicability of our proposed method to various video transcoding mechanisms. Experimental results have shown that our proposed method provides stronger robustness against video transcoding than other methods and achieves satisfactory security performance against steganalysis. Compared with some existing methods, our proposed method is more robust and reliable to realize hidden communication over social media channels, such as YouTube and Vimeo.

Most robust steganographic methods pursue insignificantly zero-bit error rate of hidden messages for ensuring the reliability of communication. Cover JPEG images are required to recompress many times for enhancing the robustness, that reduces the security. In this letter, we propose a content-aware steganographic scheme for hiding speech signals into JPEG images by utilizing the redundancy of speech signals. Firstly, we design a steganographic communication model that combines speech coding with embedding process by using embedded redundancy of speech messages. It is suitable for all lossy channels. Secondly, for improving the robustness of speech signals under a given embedding rate, we propose a content-aware protection method by exploiting different effects of speech coding parameters on speech quality after transcoding. Finally, an optimized linear prediction net (LPCNet) model is implemented to improve the end-to-end quality of speech signals. Compared with existing algorithms, experimental results show that the end-to-end quality of embedding speech is improved by 95% and the transmission efficiency is raised by 2.16 times. Meanwhile, our scheme can resist the steganalysis attack based on the JPEG recompression feature.

Due to a large number of user-uploaded images, social networks have become secure channels for covert communication. However, the JPEG recompression of social networks changes the DCT coefficients of stego images, resulting in the failure of adaptive steganography. To achieve steganography in lossy channels, robust steganography has been proposed. In this letter, the ability against JPEG recompression of robust steganography is further improved by introducing a robustness cost function. For calculating the robustness cost, a robustness model based on the spatial domain calculated from DCT coefficients is firstly proposed. Then the robustness cost is acquired by measuring the distance between the spatial pixels calculated from modified DCT coefficients and the robustness model adjusted spatial pixels. Combining the distortion function and the robustness cost function, the method proposed has considerable robustness performance while maintaining satisfying security performance. Experimental results show that with the maximum reduction of 4.04% on security performance, the algorithm proposed has a significant improvement on robustness performance compared with state-of-the-art robust steganography.

Sharing videos on social networks has become more and more popular, which provides a new scenario for covert communication. Video sharing-based hidden communication can conceal the contact relation between the sender and receiver and achieve the one-to-many delivery of secret messages. However, most video steganographic methods are unable to complete reliable hidden communication on social networks because of lossy video recompression. In this paper, we propose adaptive QIM (Quantization Index Modulation) with minimum embedding cost, which decreases the quantization distortion as much as possible to improve the security performance against steganalysis under the same level of robustness. Furthermore, based on the proposed quantization modulation scheme, we implement two robust steganographic methods in the DWT-SVD domain and the DTCWT-SVD domain. Experimental results show that the overall performance of our proposed modulation scheme outperforms QIM and adaptive QIM. Compared with existing robust video data hiding, two proposed steganographic methods demonstrate superior robustness and security on local lossy channels and social networks.

In this paper, we introduce a new approach to detect synthetic portrait images and videos. Motivated by the observation that the symmetry of synthetic facial area would be easily broken, this approach aims to reveal the tampering trace by features learned from symmetrical facial regions. To do so, a two-stream learning framework is designed which uses a hard sharing Deep Residual Networks as the backbone network. The feature extractor maps the pair of symmetrical face patches to an angular distance indicating the difference of symmetry features. Extensive experiments are carried out to test the effectiveness in detecting synthetic portrait images and videos, and corresponding results show that our approach is effective even on heterogeneous data and re-compression data that were not used to train the detection model.

Fake speech detection aims to distinguish fake speech from natural speech. This paper presents an effective fake speech detection scheme based on residual network with transformer encoder (TE-ResNet) for improving the performance of fake speech detection. Firstly, considering inter-frame correlation of the speech signal, we utilize transformer encoder to extract contextual representations of the acoustic features. Then, a residual network is used to process deep features and calculate score that the speech is fake. Besides, to increase the quantity of training data, we apply five speech data augmentation techniques on the training dataset. Finally, we fuse the different fake speech detection models on score-level by logistic regression for compensating the shortcomings of each single model. The proposed scheme is evaluated on two public speech datasets. Our experiments demonstrate that the proposed TE-ResNet outperforms the existing state-of-the-art methods both on development and evaluation datasets. In addition, the proposed fused model achieves improved performance for detection of unseen fake speech technology, which can obtain equal error rates (EERs) of 3.99% and 5.89% on evaluation set of FoR-normal dataset and ASVspoof 2019 LA dataset respectively.

The rapid development of DeepFake technologies has brought great challenges to the authenticity of video contents. It is of vital importance to develop DeepFake detection methods, among which three-dimensional (3D) convolution neural networks (CNN) have attracted wide interest and achieved satisfying performances. However, there are few 3D CNNs designed for DeepFake detection and the parameters of them are large, which cause heavy memory and storage consumption. In this paper, a lightweight 3D CNN is proposed for DeepFake detection. Channel transformation module is designed to extract features with much fewer parameters in higher level. Serving as spatial-temporal module, 3D CNNs are adopted to fuse the spatial features in time dimension. To suppress frame content and highlight frame texture, spatial rich model features are extracted from the input frames, which helps the spatial-temporal module achieve better performance. Experimental results show that the number of parameters of the proposed network is much less than those of other networks and the proposed network outperforms other state-of-the-art DeepFake detection methods on mainstream DeepFake data sets.

Current video steganography operates with either the decoded frame images or the compression coding parameters, which could cause quality degradation of the reconstructed frames. In this letter, by exploiting the advanced motion vector prediction (AMVP) technique of High Efficiency Video Coding (HEVC) standard, we propose a non-degraded adaptive steganographic approach for H.265/HEVC videos. The index value in the candidate list of the prediction unit (PU) is used for embedding. Experimental results demonstrate the superiority of the proposed steganographic approach against both hand-crafted feature-based and deep learning network-based steganalytic detectors. Our work explores a new embedding space that is not previously studied. It is a significant development in finding new ways to escape from video quality change-based steganalysis.

Social networks are everywhere and currently transmitting very large messages. As a result, transmitting secret messages in such an environment is worth researching. However, the images used in transmitting messages are usually compressed with a JPEG compression channel, which is lossy and damages the transmitted data. Therefore, to prevent secret messages from being damaged, a robust JPEG steganography is urgently needed. In this paper, a secure robust JPEG steganographic scheme based on an autoencoder with an adaptive BCH encoding (Bose-Chaudhuri-Hocquenghem encoding) is proposed. In particular, the autoencoder is first pretrained to fit the transformation relationship between the JPEG image before and after compression by the compression channel. In addition, the BCH encoding is adaptively utilized according to the content of cover image to decrease the error rate of secret message extraction. The DCT (Discrete Cosine Transformation) coefficient adjustment based on practical JPEG channel characteristics further improves the robustness and statistical security. Comparisons with prior state-of-the-art schemes demonstrate that the proposed robust JPEG steganographic algorithm can provide a more robust performance and statistical security.

To cope with the abuse of steganography using H.264 videos, i.e., the dominant video format, as the carrier, this paper presents a steganalytic method which works well even in the scenario where both the training data and the prior knowledge of the test data are limited. As a key feature of H.264, intra prediction is incorporated to remove redundancies within one single frame by predicting the current block using previously coded blocks. Unlike in JPEG domain, the quantized discrete cosine transform (QDCT) coefficients in H.264 videos come from the prediction error (residual) blocks (PEBs) instead of the original pixel block, hence we suggest shifting the focal point from the spatial domain to the prediction error domain, i.e., the PEB domain. According to the traits of video coding, 3 types of subtractive PEB (SPEB) are defined to capture the inconsistency between correlated PEBs, and the differences between correlated SPEBs are modeled by first-order Markov chain. Then the so-called SUPERB (SUbtractive Prediction ERror Block) features are engineered by subsets of sample transition probability matrices for a steganalyzer. What's more, the features derived from IPM (Intra Prediction Mode) transition probabilities are also merged into SUPERB to improve detection ability. Extensive experiments are carried out from different aspects. Performance results demonstrate the effectiveness of SUPERB, particularly its essence of general applicability when the training and test data are of quite different attributes, which is more favorable for real-world applications.

This paper proposes a novel coding strategy to achieve distortion minimization for H.264 steganography with quantized discrete cosine transform (QDCT) coefficients. Currently, with the help of syndrome-trellis codes (STCs), state-of-the-art image steganography embeds messages while minimizing a heuristically defined distortion function. However, this concept cannot be directly ported to steganography using compressed video as the cover media. According to the intra prediction principle, an H.264 QDCT coefficient block is predicted and coded based on previously encoded blocks, so even a slight embedding change will set off a chain reaction in the remaining cover blocks. Considering the cover block dependency, we make necessary changes to the standard trellis coding structure so as to be applicable for the joint compression embedding scenario. During the coding/embedding procedure, we maintain multiple contexts corresponding to possible optimal routes, and retrace each route periodically to determine how each cover block should be modified. After each modification, the remaining cover blocks, as well as their embedding costs, are re-evaluated, and each context is updated to reflect the embedding effect. In this way, the global optimality can be approached progressively in a block-by-block manner, so our proposed method is named progressive trellis coding (PTC). Extensive experiments have been conducted, and corresponding results show that the adoption of PTC brings about a significant gain in embedding performance.

Image steganalysis is a technique for detecting data hidden in images. Recent research has shown the powerful capabilities of using convolutional neural networks (CNN) for image steganalysis. However, due to the particularity of steganographic signals, there are still few reliable CNN-based methods for applying steganalysis to images of arbitrary size. In this paper, we address this issue by exploring the possibility of exploiting a network for steganalyzing images of varying sizes without retraining its parameters. On the assumption that natural image noise is similar between different image sub-regions, we propose an end-to-end, deep learning, novel solution for distinguishing steganography images from normal images that provides satisfying performance. The proposed network first takes the image as the input, then identifies the relationships between the noise of different image sub-regions, and, finally, outputs the resulting classification based upon them. Our algorithm adopts a Siamese, CNN-based architecture, which consists of two symmetrical subnets with shared parameters, and contains three phases: preprocessing, feature extraction, and fusion/classification. To validate the network, we generated datasets composed of steganography images with multiple sizes and their corresponding normal images sourced from BOSSbase 1.01 and ALASKA #2. Experimental results produced by the data generated by various methods show that our proposed network is well-generalized and robust.

The social networks transcode uploaded videos in a lossy way, which makes most video steganographic methods become unusable. In this paper, a robust video steganographic method is proposed to resist video transcoding on social networking sites. The luminance component of the raw video is selected as the cover and Quantization Index Modulation (QIM) algorithm based on block statistical features is applied to embed secret messages. To make a good tradeoff between the robustness and visual quality, an iteration in the local transcoder is designed to determine the minimum quantization step for each video. Then, a strategy of selecting robust video frames is proposed to further improve the robustness and security. To avoid sharing information beforehand between the sender and the receiver, a steganographic side channel is built for correct message extraction. Experimental results have shown that our proposed method can provide strong robustness against social networks transcoding, the average bit error rate is less than 1%. Meanwhile, our proposed method achieves a satisfactory level of security performance. It's a robust and secure method for covert communication on social networking sites such as YouTube and Vimeo.

Adaptive steganography based on minimizing additive distortion model with Syndrome-Trellis Codes (STCs) is considered as a state-of-the-art technique of covert communication. However, the running time on mobile phone with large size image is not acceptable. The current approach only accelerates STCs embedding. J-UNIWARD, as one of the most secure distortion function, its calculation time is ten times longer than STCs embedding time. Therefore, just accelerating STCs embedding will only result in a small decrease in total running time. In this letter, we propose a fast and secure steganography based on properly simplifying J-UNIWARD. A simplified distortion function based on J-UNIWARD is designed to reduce time complexity. Besides, we propose a segmented STCs, which increases the computational parallelism of STCs embedding by several times without significantly degrading the security. Experimental results demonstrate that the proposed method can be three times faster than J-UNIWARD at only a very slight price of security.

In this letter, we first propose a novel coding method to design content-adaptive H.264 steganography with quantized discrete cosine transform (QDCT) coefficients. Currently, the state-of-the-art steganographic methods minimize a heuristically defined distortion function using STCs and embed messages in a pixel-wise manner. When this concept is directly applied to H.264 steganographic designing, there are two factors that hinder the improvement of empirical security: interaction of embedding changes, and the block-wise characteristics of video compression. Our proposed CEC scheme performs both message embedding and video compression in the block-wise manner where a cluster of elements in a cover block are modified simultaneously, and defines a joint distortion function on the cover block to reflect the features of rate-distortion optimization. Experimental results demonstrate the effectiveness of our proposed coding method.

In this letter, we devise an adaptive double-layered embedding scheme that is suitable for MP3 steganography. According to the encoding characteristics of MP3, the linbits are used as the embedding domain. The proposed scheme is divided into two layers and the messages are embedded into each layer with binary STCs. The cost function used in the first layer is designed by employing the masking effect to achieve optimal imperceptibility. In order to reduce the modification of coefficients, the cost function for the second layer is revised according to the embedding results of the first layer. Experiments demonstrate that our scheme is able to achieve better acoustic concealment and higher embedding modifying efficiency indeed. In addition, our scheme can well resist the attack from the statistical handcrafted analysis methods.

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.

Recent studies have shown that convolutional neural networks (CNNs) can boost the performance of audio steganalysis. In this paper, we propose a well-designed fully CNN architecture for MP3 steganalysis based on rich high-pass filtering (HPF). On the one hand, multi-type HPFs are employed for "residual" extraction to enlarge the traces of the signal in view of the truth that signal introduced by secret messages can be seen as high-pass frequency noise. On the other hand, to utilize the spatial characteristics of feature maps better, fully connected (Fc) layers are replaced with convolutional layers. Moreover, this fully CNN architecture can be applied to the steganalysis of MP3 with size mismatch. The proposed network is evaluated on various MP3 steganographic algorithms, bitrates and relative payloads, and the experimental results demonstrate that our proposed network performs better than state-of-the-art methods.

With the rapid development of stream multimedia, the adaptive multi-rate (AMR) audio steganography are emerging recently. However, the traditional steganalysis methods face great challenges in detecting short time speech at low embedding rates. To address this problem, we propose a steganalytic scheme by combining Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN), SRCNet. AMR fixed codebook (FCB) steganography embed messages by modifying the pulse positions, which would destroy the FCB correlation. Firstly we analyzed the FCB correlations at different distances, and summarized these correlations into four categories. Furthermore, we utilizes RNN to extract higher level contextual representations of FCBs and CNN to fuse spatial-temporal features for the steganalysis. The proposed approach was evaluated on a public data-set. The experiment results validate that the proposed framework greatly outperforms the existing state-of-the-art methods. The correct detection rate of SRCNet has been improved above at least 10% when the sample is as short as 100ms at the 20% embedding rate. In particular, the network achieves the significant improvements for detecting the STCs based adaptive AMR steganography.

In this paper, a novel deblocking filtering-based VP8 steganographic scheme is proposed. The unique aspect of this work and one that distinguishes it from the prior art is that we effectively exploit the characteristics of deblocking filtering. We propose to embed the secret messages by comparing the quantized discrete cosine transform coefficients before and after the in-loop filtering. In the process of encoding, given one frame, first, we encode it to obtain the quantized discrete cosine transform coefficients. Second, a new set of coefficients is obtained by re-encoding the filtered frame. Third, the distortion function is defined by comparing the difference between the two sets of coefficients. Finally, adaptive embedding is realized by using the syndrome-trellis codes. Experimental results show that satisfactory levels of visual quality and steganographic security could be achieved with adequate payloads.

In this paper, a universal joint embedding distortion function (JED) is proposed to improve the undetectability and imperceptibility of MP3 steganography, which can be applied to Huffman codeword mapping (HCM) and sign bit flipping (SBF). Content-aware and statistical distortions are synthetically modeled to formulate the atom modification of the quantified modified discrete cosine transform (QMDCT) coefficients. On the one hand, to retain the hearing imperceptibility, the absolute threshold of hearing is employed to measure the auditory sensitivity of each QMDCT coefficient. On the other hand, considering most of the existing universal MP3 steganalysis features are designed based on correlations, the forward and backward transition probability are utilized to characterize the correlations between adjacent QMDCT coefficients. What's more, we present an implementation of JED in sign bits domain. Experimental results demonstrate that our method is able to achieve higher embedding capacity and better imperceptibility. The detection accuracy of the proposed scheme is about 75% with the bitrate of 320kbps and embedding rate of 11kbit/s, which is respectively decreased by 9.54% ~ 16.94% than existing MP3 steganographic methods.

Image steganalysis based on convolutional neural networks (CNNs) has achieved remarkable performance. However, all existing CNN-based steganalysis methods form an ensemble by merging the outputs of independently trained networks with the same architecture. In this letter, we propose a universal CNN architecture incorporating ensemble classification strategy. Any CNN-based steganalysis with the proposed architecture needs to train only one model to form an ensemble and can boost detection accuracy in both spatial and JPEG steganography. In particular, we propose a new method to construct subspaces for training well-designed base learners. In addition, a novel voting fusion structure automatically optimized with the training process is proposed. Experimental results on the public dataset demonstrate that the proposed architecture can further improve the performance of CNN-based steganalysis. Source code is available via GitHub (https://github.com/Ante-Su/CAECS).

Constrained image splicing detection and localization (CISDL), which investigates two input suspected images and identifies whether one image has suspected regions pasted from the other, is a newly proposed challenging task for image forensics. In this paper, we propose a novel adversarial learning framework to learn a deep matching network for CISDL. Our framework mainly consists of three building blocks. First, a deep matching network based on atrous convolution (DMAC) aims to generate two high-quality candidate masks, which indicate suspected regions of the two input images. In DMAC, atrous convolution is adopted to extract features with rich spatial information, a correlation layer based on a skip architecture is proposed to capture hierarchical features, and atrous spatial pyramid pooling is constructed to localize tampered regions at multiple scales. Second, a detection network is designed to rectify inconsistencies between the two corresponding candidate masks. Finally, a discriminative network drives the DMAC network to produce masks that are hard to distinguish from ground-truth ones. The detection network and the discriminative network collaboratively supervise the training of DMAC in an adversarial way. Besides, a sliding window-based matching strategy is investigated for high-resolution images matching. Extensive experiments, conducted on five groups of datasets, demonstrate the effectiveness of the proposed framework and the superior performance of DMAC.

Most current audio steganographic methods are content non-adaptive which have poor security and low embedding capacity. This paper proposes a generalized adaptive Huffman code mapping (AHCM) framework for obtaining higher secure payload. To avoid the frame-offset effect of audio codec, we first establish a distortion-limited suppressible code space, which realizes data embedding by using equal-length entropy codes. Furthermore, a stego key is used to dynamically build Huffman code mapping of each frame for improving acoustic imperceptibility and statistical undetectability. We then consider integrating psychoacoustic model (PAM) of intra-frame with frame-level perceptual distortion of inter-frame to obtain minimized total distortion. Finally, we present an implementation of the proposed AHCM framework on MP3 audios. A distortion function based on the PAM and an optimal steganographic frame path are, respectively, devised for adaptively embedding via employing syndrome-trellis codes. Experimental results demonstrate that our approach is, indeed, able to achieve higher secure steganographic capacity and better acoustic concealment. The detection accuracy of 320-kbps-mp3 datasets is lower than 65% when the embedding payload reaches 11 kbps, which is decreased by 11.8%-13.4% than the state-of-the-art steganographic methods.

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.

This paper makes the first attempt to achieve content-adaptive H.264 steganography with the quantised discrete cosine transform (QDCT) coefficients in intra-frames. Currently, state-of-the-art JPEG steganographic schemes embed their payload while minimizing a heuristically defined distortion. However, porting this concept to schemes of compressed videos remains an unsolved challenge. Because of H.264 intra prediction, the QDCT coefficient blocks are highly depended on their adjacent encoded blocks, and modifying one coefficient block will set off a chain reaction in the following cover blocks. Based on a thorough investigation into this problem, we propose two embedding strategies for cover block decoupling to inhibit the embedding interactions. With this methodology, the latest achievements in the JPEG domain are expected to be incorporated to construct H.264 steganographic schemes for better performances.

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.

This paper proposes an effective intra-frame prediction mode (IPM)-based video steganography in HEVC to maintain rate-distortion optimization as well as improve empirical security. The unique aspect of this work and one that distinguishes it from prior art is that we capture the embedding impacts on neighboring prediction units, called inter prediction unit (inter-PU) embedding impacts caused by the predictive coding widespread employed in video coding standards, using a distortion measure. To avoid the emergence of neighboring IPMs mutually affecting each other within the same channel, three-layered isolated channels are established in terms of the property of IPM coding. According to theoretical analysis for embedding impacts on the current prediction unit, called intra prediction unit (intra-PU) embedding impacts on coding efficiency (both visual quality and compression efficiency), a novel distortion function purposely designed to discourage the embedding changes with impacts on adjacent channels is proposed to express the multi-level embedding impacts. Based on the defined distortion function, two-layered syndrome-trellis codes (STCs) are utilized in practical embedding implementation alternatively. Experimental results demonstrate that the proposed scheme outperforms other existing IPM-based video steganography in terms of rate-distortion optimization and empirical security.

This paper presents an effective steganalytic scheme based on CNN for detecting MP3 steganography in the entropy code domain. These steganographic methods hide secret messages into the compressed audio stream through Huffman code substitution, which usually achieve high capacity, good security and low computational complexity. First, unlike most previous CNN based steganalytic methods, the quantified modified DCT (QMDCT) coefficients matrix is selected as the input data of the proposed network. Second, a high pass filter is used to extract the residual signal, and suppress the content itself, so that the network is more sensitive to the subtle alteration introduced by the data hiding methods. Third, the $ 1 \times 1 $ convolutional kernel and the batch normalization layer are applied to decrease the danger of overfitting and accelerate the convergence of the back-propagation. In addition, the performance of the network is optimized via fine-tuning the architecture. The experiments demonstrate that the proposed CNN performs far better than the traditional handcrafted features. In particular, the network has a good performance for the detection of an adaptive MP3 steganography algorithm, equal length entropy codes substitution (EECS) algorithm which is hard to detect through conventional handcrafted features. The network can be applied to various bitrates and relative payloads seamlessly. Last but not the least, a sliding window method is proposed to steganalyze audios of arbitrary size.

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.

This paper presents an effective steganalytic algorithm to detect Discrete Cosine Transform (DCT) based data hiding methods for H.264/AVC videos. These methods hide covert information into compressed video streams by manipulating quantized DCT coefficients, and usually achieve high payload and low computational complexity, which is suitable for applications with hard real-time requirements. In contrast to considerable literature grown up in JPEG domain steganalysis, so far there is few work found against DCT-based methods for compressed videos. In this paper, the embedding impacts on both spatial and temporal correlations are carefully analyzed, based on which two feature sets are designed for steganalysis. The first feature set is engineered as the histograms of noise residuals from the decompressed frames using 16 DCT kernels, in which a quantity measuring residual distortion is accumulated. The second feature set is designed as the residual histograms from the similar blocks linked by motion vectors between inter-frames. The experimental results have demonstrated that our method can effectively distinguish stego videos undergone DCT manipulations from clean ones, especially for those of high qualities.

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.

This paper presents a steganalytic approach against video steganography which modifies motion vector (MV) in content adaptive manner. Current video steganalytic schemes extract features from fixed-length frames of the whole video and do not take advantage of the content diversity. Consequently, the effectiveness of the steganalytic feature is influenced by video content and the problem of cover source mismatch also affects the steganalytic performance. The goal of this paper is to propose a steganalytic method which can suppress the differences of statistical characteristics caused by video content. The given video is segmented to subsequences according to block’s motion in every frame. The steganalytic features extracted from each category of subsequences with close motion intensity are used to build one classifier. The final steganalytic result can be obtained by fusing the results of weighted classifiers. The experimental results have demonstrated that our method can effectively improve the performance of video steganalysis, especially for videos of low bitrate and low embedding ratio.

This paper presents a steganalytic approach against motion vector-based video steganography that does not depend on the detailed knowledge of embedding algorithms. In most state-of-the-art video coding standards, the motion vector is the result of block-based motion estimation using rate-distortion optimization. That is to say, each motion vector is locally optimal in a rate-distortion sense, and any modification will inevitably shift the motion vector from locally optimal to non-optimal. As a consequence, it is a very strong evidence of steganography if some motion vectors are found to be locally non-optimal. Based on this fact, the core of our method is an estimator to check the local optimality of motion vectors in a rate-distortion sense. We try to recover the necessary information used for motion vector decision that is lost during lossy compression, based on which a 36-D feature set is formed for training and classification. To demonstrate the effectiveness of the proposed approach, experiments are carried out in different settings. The corresponding results show that our approach has a wide applicability even at low embedding strengths. Particularly, the problem of cover source mismatch is largely alleviated, which indicates that the proposed approach is suitable to be used in situations where a very limited priori knowledge is available.

This paper presents an effective motion vector (MV)-based steganography to cope with different steganalytic models. The main principle is to define a distortion scale expressing the multi-level embedding impact of MV modification. Three factors including motion characteristic of video content, MV's local optimality and statistical distribution are considered in distortion definition. For every embedding location, the contributions of three factors are dynamically adjusted according to MV's property. Based on the defined distortion function, two layered syndrome-trellis codes (STCs) are utilized to minimize the overall embedding impact in practical embedding implementation. Experimental results demonstrate that the proposed method achieves higher level of security compared with other existing MV-based approaches, especially for high quality videos.

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.

The goal of this paper is to improve the performance of the current video steganalysis in detecting motion vector (MV)-based steganography. It is noticed that many MV-based approaches embed secret bits in content adaptive manners. Typically, the modifications are applied only to qualified MVs, which implies that the number of modified MVs varies among frames after embedding. On the other hand, nearly all the current steganalytic methods ignore such uneven distribution. They divide the video into frame groups equally and calculate every single feature vector using all MVs within one group. For better classification performances, we suggest performing steganalysis also in an adaptive way. First, divide the video into groups with variable lengths according to frame dynamics. Then within each group, calculate a single feature vector using all suspicious MVs (MVs that are likely to be modified). The experimental results have shown the effectiveness of our proposed strategy.

In this paper, a novel motion vector-based video steganographic scheme is proposed, which is capable of withstanding the current best statistical detection method. With this scheme, secret message bits are embedded into motion vector (MV) values by slightly perturbing their motion estimation (ME) processes. In general, two measures are taken for steganographic security (statistical undetectability) enhancement. First, the ME perturbations are optimized ensuring the modified MVs are still local optimal, which essentially makes targeted detectors ineffective. Secondly, to minimize the overall embedding impact under a given relative payload, a double-layered coding structure is used to control the ME perturbations. Experimental results demonstrate that the proposed scheme achieves a much higher level of security compared with other existing MV-based approaches. Meanwhile, the reconstructed visual quality and the coding efficiency are slightly affected as well.

In this paper, with a novel data representation named macroblock partition mode, an effective steganography integrated with H.264/AVC compression is proposed. The main principle is to improve the steganographic security in two directions. First, to embed messages, an internal process of H.264 compression, i.e., the macroblock partition, is slightly perturbed, hence the compression compliance is ensured. Second, to minimize the embedding impact, a high efficient double-layered structure is deliberately designed. In the first layer, the syndrome-trellis codes (STCs) is utilized to perform adaptive embedding, and the costs in visual quality and compression efficiency are both considered to construct the distortion model. In the second layer, facilitated by the wet paper codes (WPCs), an expected 3-bit per change gain in embedding efficiency is obtained.

Recently, code construction approaching the rate-distortion bound of reversible data hiding has been proposed by Lin , in which the coding/decoding process needs the optimal probability distribution of marked-signals as parameters. Therefore, the efficiency and accuracy of estimating the optimal marked-signal distribution will greatly influence the speeds of encoding and decoding. In this paper, we propose a fast algorithm to solve the optimal marked-signal distribution. Furthermore, we modify the method to achieve the optimal distribution directly according to a given distortion constraint or an expected embedding rate, which makes it more practical for applications.

Recently, more and more attention is paid to reversible data hiding (RDH) in encrypted images, since it maintains the excellent property that the original cover can be losslessly recovered after embedded data is extracted while protecting the image content's confidentiality. All previous methods embed data by reversibly vacating room from the encrypted images, which may be subject to some errors on data extraction and/or image restoration. In this paper, we propose a novel method by reserving room before encryption with a traditional RDH algorithm, and thus it is easy for the data hider to reversibly embed data in the encrypted image. The proposed method can achieve real reversibility, that is, data extraction and image recovery are free of any error. Experiments show that this novel method can embed more than 10 times as large payloads for the same image quality as the previous methods, such as for PSNR=40 dB.

Unlike traditional image or video steganography in spatial/transform domain, motion vector (MV)-based methods target the internal dynamics of video compression and embed messages while performing motion estimation. However, we have noticed that some existing methods adopt nonoptimal selection rules and modify MVs in somewhat arbitrary manners which violate the encoding principles a lot. Aiming at these weaknesses, we design a calibration-based approach and propose MV reversion-based features for steganalysis. Experimental results demonstrate that the proposed features are very sensitive to the tendency of MV reversion during calibration and can be used to effectively detect some typical MV-based steganography even with low embedding rates.

It was reported that a multivariate public key cryptosystem (MPKC) could be strengthened if its public key is generated by composition of two original public keys. In fact, two existing keys are used to constitute two quadratic rounds of the new key. But such a two-round scheme, called 2R, was claimed to have been decomposed, and even a further improved 2R, named 2R−, was shown to be similarly vulnerable. The result casts doubts on the principle of using a two-round structure to improve the security. However, this study clearly states that the decomposition attacks depend on the prerequisite that either of the rounds is quadratic. It shows that these attacks, even the conceivable extended ones, do not work in theory or in practice if the first round is of higher degree, although the threat still remains when only the degree of the second round is changed. Therefore adopting a cubic first round becomes a rule in the design of the 2-round schemes. The analysis and experiments in this study also demonstrate that the new schemes with such an indecomposable two-round public key can provide the desired security against many other known and potential attacks on MPKCs and that the key size can be practically controlled.