Jing Ren

To address the current issue that existing steganographic techniques are highly dependent on the quality of carrier images and have insufficient adaptability to damaged images, we propose an MAE-based inpainting-steganography framework, which realizes steganography and inpainting for 2D color damaged images through multi-module collaboration. The encoder divides the original 244 × 244 images into non-overlapping patches and performs random masking to generate their feature sequences. The steganographic point prediction module locates suitable steganographic points by analyzing feature fluctuations during the inpainting process. The steganography module embeds information by introducing feature offsets at specific positions in the feature sequences according to the suitable steganographic points. The decoder completes the inpainting of masked regions to obtain stego-inpainted images. And the extraction module recovers the secret information through feature alignment. Experimental results show that with a feature fluctuation amplitude threshold of 0%, an offset of 3%, and an embedding capacity of 30 bits, the verification success rate reaches 96.67%, and remains at 95.27% even when the capacity is increased to 1000 bits. In terms of anti-steganography detection capability, evaluation results based on mainstream steganalysis models show that the detection accuracy of the proposed method is 49.79%. This accuracy is close to the level of random guessing, which indicates the excellent anti-detection performance of the method. Moreover, under the combined perturbations of JPEG compression, Gaussian blur, and noise interference, the information extraction accuracy still reaches 94.68%, demonstrating that the feature-domain embedding mechanism has good robustness. In addition, adding steganography under different masking ratios has no significant impact on image inpainting performance, and some metrics even outperform pure inpainting algorithms. While maintaining the quality of image inpainting, this framework achieves highly reliable information embedding and extraction, and maintains a high verification success rate in the complex scenario of damaged carrier images, providing a new idea for steganographic techniques in practical applications.

The Social Internet of Things (SIoT) combines social networks and the Internet of Things, enabling closer interaction between devices, users, and services. However, this interaction brings risks of trust attacks. These trust attacks not only affect the stability of SIoT systems but also threaten personal privacy and data security. This paper provides a decade-long review of SIoT trust attack research. First, it outlines the SIoT architecture, social relationship types, concept of trust, and trust management processes. It maps seven attacks—bad mouthing attack (BMA), ballot stuffing attack (BSA), self-promoting attack (SPA), discriminatory attack (DA), whitewashing attack (WWA), on-off attack (OOA), and opportunistic service attack (OSA)—clarifying their mechanisms and traits. Next, we synthesize the literature on SIoT trust models, enumerate which attack types they address, and classify defense strategies. It then conducts simulation-based comparative experiments on trust attacks to reveal their impact on node trust and transaction processing, compares attack capabilities along disruption speed, attack strength, and stealthiness, and summarizes attack surfaces with corresponding defense recommendations to better guide the design of SIoT trust management schemes. Finally, we identify open challenges and future research directions, to support the development of new trust management models better equipped to address evolving trust attacks.

To address the accuracy issues in monocular depth estimation caused by insufficient feature extraction and inadequate context modeling, a multi-scale feature optimization model named EFDepth was proposed to improve prediction performance. This framework adopted an encoder–decoder structure: the encoder (EC-Net) was composed of MobileNetV3-E and ETFBlock, and its features were optimized through multi-scale dilated convolution; the decoder (LapFA-Net) combined the Laplacian pyramid and the FMA module to enhance cross-scale feature fusion and output accurate depth maps. Comparative experiments between EFDepth and algorithms including Lite-mono, Hr-depth, and Lapdepth were conducted on the KITTI datasets. The results show that, for the three error metrics—RMSE (Root Mean Square Error), AbsRel (Absolute Relative Error), and SqRel (Squared Relative Error)—EFDepth is 1.623, 0.030, and 0.445 lower than the average values of the comparison algorithms, respectively, and for the three accuracy metrics, it is 0.052, 0.023, and 0.011 higher than the average values of the comparison algorithms, respectively. Experimental results indicate that EFDepth outperforms the comparison methods in most metrics, providing an effective reference for monocular depth estimation and 3D reconstruction of complex scenes.

Existing network intrusion detection models effectively capture relationships between nodes and extract key features. However, they often struggle to accurately represent node characteristics, particularly in modeling the spatiotemporal dynamics and topological structures with sufficient granularity. To address these limitations, we propose the dynamic interaction multi-channel graph convolutional network (DIMK-GCN), which integrates three key components: a spatiotemporal feature weighting module, an interactive graph feature fusion module, and a temporal feature learning module. The spatiotemporal feature weighting module constructs a dynamic graph structure that incorporates both nodes and edges, leveraging self-attention mechanisms to enhance critical feature representations. The interactive graph feature fusion module employs graph attention networks (GATs) to refine node relationships while integrating a multi-channel graph convolutional network (GCN) to extract multi-perspective features, thereby enhancing model depth and robustness. The temporal feature learning module utilizes gated recurrent units (GRUs) to effectively capture long-term dependencies and address challenges posed by non-stationary time series data. Experimental results on the CIC-IDS2017, CIC-IDS2018, and Edge-IIoTSet datasets demonstrate that DIMK-GCN significantly outperforms existing models in key performance metrics, including detection accuracy, recall, and F1-score. Notably, on the Edge-IIoTSet dataset, DIMK-GCN achieves an accuracy of 97.31%, verifying its effectiveness and robustness in detecting various types of network attacks.

The surface texture of objects in industrial scenes is complex and diverse, and the characteristics of surface defects are often very similar to the surrounding environment and texture background, so it is difficult to accurately detect the defect area. However, when deep learning technology is used to detect complex texture surface defects, the detection accuracy is not high, due to the lack of large-scale pixel-level label datasets. Therefore, a defect detection model Siamese-RCNet for complex texture surface with a small number of annotations is proposed. The Cascade R-CNN target detection network is used as the basic framework, making full use of unlabeled image feature information, and fusing the nonlinear relationship learning ability of Siamese network and the feature extraction ability of the Res2Net backbone network to more effectively capture the subtle features of complex texture surface defects. The image difference measurement method is used to calculate the similarity between different images, and the attention module is constructed to weight the feature map of the feature extraction pyramid, so that the model can focus more on the defect area and suppress the influence of complex background texture area, so as to improve the accuracy of detection. To verify the effectiveness of the Siamese-RCNet model, a series of experiments were carried out on the DAGM2007 dataset of weakly supervised learning texture surface defects for industrial optical inspection. The results show that even if only 20% of the labeled datasets are used, the mAP@0.5 of the Siamese-RCNet model can still reach 96.9%. Compared with the traditional Cascade R-CNN and Faster R-CNN target detection networks, the Siamese-RCNet model has high accuracy, can reduce the workload of manual labeling, and provides strong support for practical applications.

With the continuous development of autonomous driving, real-time target detection has become increasingly critical in autonomous driving systems. However, traditional target detection algorithms usually require huge computational resources, limiting their application on embedded autonomous driving platforms. To address this challenge, a lightweight single-stage target detection algorithm is proposed YOLOdrive. The inverted residual structure, linear bottleneck layer, and depth-separable convolution in MobileNetv2 are utilized to improve the YOLOv8 backbone network, while the spatial channel reconstructed convolution is used to improve the C2f module of YOLOv8, and the convolution of YOLOv8 neck and detection head is replaced by the depth-separable convolution. Experimental results verify that the average accuracy of YOLOdrive algorithm on MS COCO2017 dataset and VOC2007 dataset is improved compared with the baseline model YOLOv8n. The amount of model parameters has been reduced by more than 50%, and the amount of computation in the model has been reduced by more than 70%. The algorithm drastically reduces the amount of parameters and computational complexity of the network, improves the operational efficiency, saves the storage space of the network, and maintains a high detection performance.

Credit risk assessment is an important process in bank financial risk management. Traditional machine-learning methods cannot solve the problem of data islands and the high error rate of two-way decisions, which is not conducive to banks’ accurate credit risk assessment of users. To this end, this paper establishes a federated three-way decision incremental naive Bayes bank user credit risk assessment model (FTwNB) that supports asymmetric encryption, uses federated learning to break down data barriers between banks, and uses asymmetric encryption to protect data security for federated processes. At the same time, the model combines the three-way decision methods to realize the three-way classification of user credit (good, bad and delayed judgment), so as to avoid the loss of bank interests caused by the forced division of uncertain users. In addition, the model also incorporates incremental learning steps to eliminate training samples with poor data quality to further improve the model performance. This paper takes German Credit data and Default of Credit Card Clients data as examples to conduct simulation experiments. The result shows that the performance of the FTwNB model has been greatly improved, which verifies that it has good credit risk assessment capabilities.

Aiming at the fact that the moving target defense game model fails to accurately portray attack and defense gains, resulting in bias in attack and defense games and the inability to select effective defense strategies, we construct the moving target three-way evolutionary game defense model (MTTEGDM). Firstly, the model is defined and analyzed theoretically under the premise of uncertainty and irrationality. Then, combined with the three-way decisions, the attack intention is introduced into the target network loss calculation, and a dynamic weight adjustment algorithm based on the three-way decisions is proposed to accurately characterize the attack and defense gains from a multi-attribute perspective. Finally, the evolutionary game model is used to analyze the evolution trend of the multi-stage defense strategy, so as to carry out feasible and effective defense behavior. The simulation results show that the model can accurately predict the optimal defense strategy of moving targets in different stages. Through a Monte Carlo simulation experiment, the proposed algorithm is compared with the traditional evolutionary game model, and the effectiveness and security of the proposed algorithm are verified.

With a large number of intrusion detection datasets and high feature dimensionality, the emergent nature of new attack types makes it impossible to collect network traffic data all at once. The modified three-way attribute reduction method is combined with a Self-Organizing Incremental learning Neural Network (SOINN) algorithm to propose a self-organizing incremental neural network intrusion detection model based on three-way attribute reduction. Attribute importance is used to perform attribute reduction, and the data after attribute reduction are fed into a self-organized incremental learning neural network algorithm, which generalizes the topology of the original data through self-organized competitive learning. When the streaming data are transferred into the model, the inter-class insertion or node fusion operation is performed by comparing the inter-node distance and similarity threshold to achieve incremental learning of the model streaming data. The inter-node distance value is introduced into the weight update formulation to replace the traditional learning rate and to optimize the topological structure adjustment operation. The experimental results show that T-SOINN achieves high precision and recall when processing intrusion detection data.