Existing counting models suffer significant performance degradation when tested on data from unknown scenarios (out-of-distribution data), due to the domain shift problem. In practical applications, it is crucial that the model exhibits robust generalization capability without relying on the target domain. This study proposes a novel domain generalization network, GFCount, which involves an innovative meta-learning strategy that leverages graphs to capture the inter-image relevance, thereby facilitating the partitioning of data into pseudo-source and pseudo-target domains. Furthermore, to strengthen the distinction between domain-relevant and domain-invariant features, we devise a feature disentanglement method that integrates style normalization with memory spaces. Finally, we formulate a tailored counting loss function specifically designed for domain generalization, aiming to disentangle features and enhance the quality of the generated density maps. Compared with the advanced approaches, GFCount achieves state-of-the-art results on three public benchmarks, with counting errors on SHB→SHA significantly decreasing by 14.2%.

Genomic prediction is a crucial technique for phenotype estimation, with the genomic best linear unbiased prediction (GBLUP) being the most widely adopted method. Yet, GBLUP falls short in capturing the intricate nonlinear relationships between genomic data and phenotypes. Given its ability to more effectively capture nonlinear genetic effects, machine learning (ML) has become increasingly appealing in genomic prediction. However, almost GBLUP and ML methods utilize all single nucleotide polymorphisms (SNPs) data for prediction, ignoring the fact that only a subset of SNPs are effective. This not only consumes computation time but also has poor prediction accuracy. So, this paper proposed a mutual information stacking method (MISM). Firstly, mutual information was introduced to select the SNPs with effect and remove the redundant SNPs. Then, we constructed a stacking model that can capture both linear and nonlinear relationships between SNPs and phenotypes to improve the prediction accuracy. To assess the effectiveness of MISM, we compared its performance on pig growth traits with GBLUP and other ML methods. The statistical analysis results indicated that MISM outperformed other ML models and GBLUP.

Heterogeneous domain adaptation (HDA) aims to address the transfer learning problems where the source domain and target domain are represented by heterogeneous features. The existing HDA methods based on matrix factorization have been proven to learn transferable features effectively. However, these methods only preserve the original neighbor structure of samples in each domain and do not use the label information to explore the similarity and separability between samples. This would not eliminate the cross-domain bias of samples and may mix cross-domain samples of different classes in the common subspace, misleading the discriminative feature learning of target samples. To tackle the aforementioned problems, we propose a novel matrix factorization-based HDA method called HDA with generalized similarity and dissimilarity regularization (HGSDR). Specifically, we propose a similarity regularizer by establishing the cross-domain Laplacian graph with label information to explore the similarity between cross-domain samples from the identical class. And we propose a dissimilarity regularizer based on the inner product strategy to expand the separability of cross-domain labeled samples from different classes. For unlabeled target samples, we keep their neighbor relationship to preserve the similarity and separability between them in the original space. Hence, the generalized similarity and dissimilarity regularization is built by integrating the above regularizers to facilitate cross-domain samples to form discriminative class distributions. HGSDR can more efficiently match the distributions of the two domains both from the global and sample viewpoints, thereby learning discriminative features for target samples. Extensive experiments on the benchmark datasets demonstrate the superiority of the proposed method against several state-of-the-art methods.

Existing linguistic steganalysis methods require the training and testing datasets to be independent and identically distributed (i.i.d). However, in real-world scenarios, various types of text and steganographic algorithms are employed to generate steganographic text, making it challenging to fulfill the requirement of independent and identical distribution between training and test datasets. This issue, known as the domain mismatch problem, significantly diminishes the detection performance. Thus, it is reasonable to consider domain adaptation by reducing the distribution discrepancy of different domains. However, how to measure and minimize the discrepancy for linguistic steganalysis remains a big challenge. In this paper, we put forward a cross-domain linguistic steganalysis architecture based on a new domain distance metric and adaptive weight selection network. Concretely, a novel steganographic domain distance metric (SDDM) is first proposed, which can effectively characterize the overall distribution discrepancy and capture the weak noise introduced by the information embedding process. Additionally, an adaptive weight selection network with a switching-path structure is designed to calculate domain-specific attention weights, facilitating the model to adapt to various discrepancies scenarios and enhancing its domain-invariant feature representation capability. Extensive experiments show that the proposed method achieves state-of-the-art performance for cross-domain linguistic steganalysis.

Feature-based domain adaptation methods project samples from different domains into the same feature space and try to align the distribution of two domains to learn an effective transferable model. The vital problem is how to find a proper way to reduce the domain shift and improve the discriminability of features. To address the above issues, we propose a unified Probability-based Graph embedding Cross-domain and class Discriminative feature learning framework for unsupervised domain adaptation (PGCD). Specifically, we propose novel graph embedding structures to be the class discriminative transfer feature learning item and cross-domain alignment item, which can make the same-category samples compact in each domain, and fully align the local and global geometric structure across domains. Besides, two theoretical analyses are given to prove the interpretability of the proposed graph structures, which can further describe the relationships between samples to samples in single-domain and cross-domain transfer feature learning scenarios. Moreover, we adopt novel weight strategies via probability information to generate robust centroids in each proposed item to enhance the accuracy of transfer feature learning and reduce the error accumulation. Compared with the advanced approaches by comprehensive experiments, the promising performance on the benchmark datasets verify the effectiveness of the proposed model.

Recently, due to the considerable feature expression ability of neural networks, deep linguistic steganalysis methods have been greatly developed. However, there are still two issues that need to be ameliorated. First, the prevailing linguistic steganalysis methods rely heavily on massive training data, which is labor-intensive and time-consuming. Second, these methods implement steganalysis only in different weak-concealed scenarios, the stego texts in each of which have only a single language style and payload. But in practice, the intercepted network samples are probably the mixture of the stego texts that possess different language styles and payloads, in which the semantic spatial distribution may be more chaotic than that in weak-concealed scenarios, thus making steganalysis more difficult. To address the above issues, a novel linguistic steganalysis method is proposed in this letter. First, the pre-trained BERT language model is constructed as an embedder to compensate for the shortage of data. Then, in addition to learning local and global semantic features, a feature interaction module is designed for exploring mutual effects between them. Furthermore, besides the typical cross-entropy loss, triplet loss is also introduced for the model training. In this way, the proposed method can refine more comprehensive and discriminative deep features in the intricate semantic space. The performance of the proposed method is compared with the representative linguistic steganalysis methods on datasets of different scales, and the experimental results reveal the superiority of the proposed method.

Text has become one of the most extensively used digital media in Internet, which provides steganography an effective carrier to realize confidential message hiding. Nowadays, generation-based linguistic steganography has made a significant breakthrough due to the progress of deep learning. However, previous methods based on recurrent neural network have two deviations including exposure bias and embedding deviation, which seriously destroys the security of steganography. In this article, we propose a novel linguistic steganographic model based on adaptive probability distribution and generative adversarial network, which achieves the goal of hiding secret messages in the generated text while guaranteeing high security performance. First, the steganographic generator is trained by using generative adversarial network to effectively tackle the exposure bias, and then the candidate pool is obtained by a probability similarity function at each time step, which alleviates the embedding deviation through dynamically maintaining the diversity of probability distribution. Third, to further improve the security, a novel strategy that conducts information embedding during model training is put forward. We design various experiments from different aspects to verify the performance of the proposed model, including imperceptibility, statistical distribution, anti-steganalysis ability. demonstrate that our proposed model outperforms the current state-of-the-art steganographic schemes.

With the emergence of the generation-based steganography, the traditional text steganalysis methods show the unsatisfactory detection performance as the manually extracted features are simple and non-universal. The recently proposed deep learning-based text steganalysis methods can obtain the great detection accuracy by extracting the high-level features. In this letter, a hybrid text steganalysis method (R-BILSTM-C) is proposed through combining the advantages of Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM) and Convolutional Neural Network (CNN). The proposed method can efficiently capture both local features and long-term semantic information from text to improve the detection accuracy. In the proposed method, the Bi-LSTM architecture is used to capture the long-term semantic information of texts. And the asymmetric convolution kernels with different sizes are applied to extract the local relationship between words. In addition, the high dimensional semantic feature space is visualized. Experimental results show that the proposed method adapts to the different steganographic algorithms efficiently, and achieves the comparable or superior detection performance for the various sentence lengths compared with other state-of-the-art text steganalysis methods.

The prevailing text steganalysis methods detect steganographic communication by extracting hand-crafted features and classifying them using SVM. However, these features are designed based on the statistical changes caused by steganography, thus they are difficult to adapt to different kinds of embedding algorithms and the detection performance is heavily dependent on the text size. In this letter, we propose a novel text steganalysis model based on convolutional neural network, which is able to capture complex dependencies and learn feature representations automatically from the texts. First, we use a word embedding layer to extract the semantic and syntax feature of words. Second, the rectangular convolution kernels with different sizes are used to learn the sentence features. To further improve the performance, we present a decision strategy for detecting the long texts. Experimental results show that the proposed method can effectively detect different kinds of text steganographic algorithms and achieve comparable or superior performance for a wide variety of text sizes compared with the previous methods.