Data hiding is a technology that embeds data into a cover carrier in an imperceptible way while still allowing the hidden data to be extracted accurately from the stego-carrier, which is one important branch of computer science and has drawn attention of scholars in the last decade. Turtle shell-based (TSB) schemes have become popular in recent years due to their higher embedding capacity (EC) and better visual quality of the stego-image than most of the none magic matrices based (MMB) schemes. This paper proposes a two-layer turtle shell matrix-based (TTSMB) scheme for data hiding, in which an extra attribute presented by a 4-ary digit is assigned to each element of the turtle shell matrix with symmetrical distribution. Therefore, compared with the original TSB scheme, two more bits are embedded into each pixel pair to obtain a higher EC up to 2.5 bits per pixel (bpp). The experimental results reveal that under the condition of the same visual quality, the EC of the proposed scheme outperforms state-of-the-art data hiding schemes.

With the rise of non-volatile memory used in cloud service, it becomes urgent to reduce the write cost so as to improve the data manipulation capability. This paper proposed a high embedding efficiency reversible data hiding scheme for encrypted images (RDH-EI). It embeds data at the locations of most significant bit (MSB) using matrix encoding, resulting in a high embedding efficiency. In order to restore the image completely at the receiver side, a highly accurate MSB prediction based on orthogonal projection technique is preprocessed on the original image and the prediction result is self-embedded to help recover the image. The experimental results verify that the proposed scheme outperforms the previous related schemes, it can achieve a higher embedding capacity of 0.412 bits per pixel at average, moreover, a significantly higher embedding efficiency of 3.43 bits per change is obtained. That means the proposed scheme can reduce the write cost by minimizing the modification in the case of the same payload and is especially suitable for applications used the non-volatile memory. Meanwhile, the process of data extraction is error free and the image can be recovered completely.

Graph Neural Networks (GNNs) are deep learning models specifically designed for analyzing graph-structured data, capturing complex relationships and structures to improve analysis and prediction. A common task in GNNs is node classification, where each node in the graph is assigned a predefined category. The Graph Attention Network (GAT) is a popular variant of GNNs known for its ability to capture complex dependencies by assigning importance weights to nodes during information aggregation. However, the GAT’s reliance on local attention mechanisms limits its effectiveness in capturing global information and long-range dependencies. To address this limitation, we propose a new attention mechanism called Global-Local Graph Attention (GLGA). Our mechanism enables the GAT to capture long-range dependencies and global graph structures while maintaining its ability to focus on local interactions. We evaluate our algorithm on three citation datasets (Cora, Citeseer, and Pubmed) using multiple metrics, demonstrating its superiority over other baseline models. The proposed GLGA mechanism has been proven to be an effective solution for improving node classification tasks.

This paper proposed a high capacity reversible data hiding (RDH) scheme using three steganographic images, on which three successive embedding phases are performed. An embedding rule is elaborately designed to guide the data embedding and three alike stego-images are generated in the first phase. In view of the similarity of three stego-images, the pixel value ordering (PVO) strategy is utilized in the second phase. In the third phase, the prediction error histogram shifting (PEHS) strategy is employed by exploiting the slight difference among three temporary stego-images. Since no complex operation is involved, the algorithm is efficient. The experimental results verify that our method is superior to other schemes in both EC and image quality. Moreover, the proposed scheme can successfully resist the RS steganalysis and provide a secure secret transmission.