Xinhua Dong

Semi-supervised learning (SSL) is critical for medical image segmentation but often struggles with network dependency and pseudo-label error accumulation. To address these issues, we propose a fractal-dimension-guided hierarchical contrastive learning dual-student framework(FD-HCL). We extend the Mean Teacher architecture with a dual-student design and introduce an independence-aware exponential moving average (I-EMA) update mechanism to mitigate model coupling. For enhanced feature learning, we devise a hierarchical contrastive learning (HCL) mechanism guided by voxel uncertainty, spanning global, high-confidence, and low-confidence regions. We further improve structural integrity by incorporating a fractal-dimension (FD)-weighted consistency loss and integrating a novel uncertainty-aware bidirectional copy–paste (UB-CP) augmentation. Extensive experiments on the LA and BraTS 2019 datasets demonstrate the state-of-the-art performance of our framework across 10% and 20% labeled data settings. On the LA dataset with 10% labeled data, our method achieved a Dice score that outperformed the best existing approach by 0.68%. Similarly, under the 10% labeling setting on the BraTS 2019 dataset, we surpassed the state-of-the-art Dice score by 0.55%.

Graph anomaly detection (GAD) is crucial for safeguarding the integrity and security of complex systems, such as social networks and financial transactions. Despite the advances made by Graph Neural Networks (GNNs) in the field of GAD, existing methods still exhibit limitations in capturing subtle structural anomaly patterns: they typically over-rely on reconstruction error, struggle to fully exploit structural similarity among nodes, and fail to effectively integrate attribute and structural information. To tackle these challenges, this paper proposes a structure-aware dual-path attention graph node anomaly detection method (DPGAD). DPGAD employs wavelet diffusion to extract network neighborhood features for each node while incorporating a dual attention mechanism to simultaneously capture attribute and structural similarities, thereby obtaining richer feature details. An adaptive gating mechanism is then introduced to dynamically adjust the fusion of attribute features and structural features. This allows the model to focus on the most relevant features for anomaly detection, enhancing its robustness and antinoise capability. Our experimental evaluation across multiple real-world datasets demonstrates that DPGAD consistently surpasses existing methods, achieving average improvements of 9.06% in AUC and 11% in F1-score. Especially in scenarios where structural similarity is crucial, DPGAD has a performance advantage of more than 20% compared with the most advanced methods.

Most GAN-based methods utilize semantic layouts as input for generating realistic images. However, these layouts primarily consist of object contours and often lack detailed information, leading to suboptimal image quality in the generated outputs. To address this limitation, we propose a novel GAN architecture called LMCGAN designed specifically for synthesizing high-quality images. LMCGAN introduces a generator network structured around the laplacian pyramid, enabling the simultaneous generation of multi-scale feature maps.This approach allows the model to capture finer details at different resolutions, enhancing the overall realism of the generated images.To further improve the utilization of semantic maps, we integrate a multi-scale channel attention (MSCA) mechanism.This mechanism effectively focuses on channel-specific information in complex scenes, which is crucial for preserving essential details that may otherwise be lost. During the feature fusion phase, we implement a feature fusion block (FFBL) that is designed to capture important relationships across various scales. This block facilitates the integration of information from different resolutions, ensuring that the final output retains critical features. Additionally, we adopt a combination of conditional and unconditional methods to reduce noise during the training process, leading to more stable and effective training dynamics. Extensive experiments conducted on challenging datasets demonstrate that LMCGAN significantly outperforms existing methods in terms of both visual quality and quantitative evaluation metrics. The results indicate that our architecture not only generates more realistic images but also excels in preserving intricate details, marking a substantial advancement in the field of image synthesis using GANs.

With the development of cloud computing and big data, data security and privacy protection in multi-user environments have become particularly important. Existing encryption schemes exhibit significant deficiencies in addressing the flexible revocation of user attributes and dynamic changes in access permissions, leading to unauthorized users illicitly accessing and tampering with data. Therefore, we propose a Blockchain-based Traceable Multi-Level Revocable Attribute-Based Encryption Scheme (BTMAR-ABE). This scheme combines the advantages of Attribute-Based Encryption (ABE) technology and blockchain, achieving real-time attribute updates and verification through smart contracts, thereby avoiding reliance on a single centralized management server and introducing uniquely associated random numbers to prevent collusion attacks. To achieve flexible and secure data access control, we designed a multi-level revocation mechanism for both temporary and permanent revocation to address short-term and long-term permission change requirements. Performance evaluation and security analysis indicate that the BTMAR-ABE scheme can effectively resist chosen plaintext attacks, attribute revocation attacks, and collusion attacks, while demonstrating significant efficiency advantages in computational cost. Simulation results further demonstrate that this scheme has high practical value in data security and access control.

Due to its partially decentralized and highly scalable features, the consortium blockchain has currently overtaken other blockchain technologies as the one most frequently used and studied across various industries. However, performance issues such as low transaction efficiency and redundant communication processes continue to hinder the development of consortium blockchains. In the Hyperledger Fabric consortium blockchain system, transaction efficiency is largely influenced by the consensus protocol and broadcast protocol. This paper introduces a novel consortium blockchain network model, DC-SoC, focused on optimizing broadcast protocols. By incorporating the concept of density clustering, a stable propagation structure is established for the blockchain network, thus optimizing data dissemination in the Gossip protocol. Additionally, the concept of social networks is integrated, using trustworthiness scores and economic incentives to evaluate node security. The experimental results demonstrate that when DC-SoC is applied in a large-scale consortium blockchain environment, it significantly improves communication performance between nodes and ensures transmission reliability.

The Internet of Things (IoT) has expanded rapidly, generating vast amounts of data that require effective protection. Traditionally, the attribute-based searchable encryption (ABSE) as been used within IoT to maintain data privacy and integrity. However, existing ABSE approaches often rely on centralized systems that are susceptible to single-point failures and are inefficient in terms of decryption and data retrieval. Therefore, we propose a novel blockchain-assisted multi-keyword searchable encryption scheme (BAMKSE) that utilizes the decentralized nature of blockchain to overcome these limitations. This scheme integrates ciphertext policy attribute-based encryption (CP-ABE) with key policy attribute-based encryption (KP-ABE) to provide advanced access control and mutual authentication, while offloading the computational burden of decryption to cloud-based pre-decryption services. Security analyses demonstrate the resilience of BAMKSE against chosen keywords attacks (CKAs), offering an effective solution for secure and efficient IoT data handling.

The information sharing among internet-connected vehicles is close, but there may be the issue of vehicles providing false information. This paper proposes a new incentive mechanism scheme for VANET to provide a decentralized and trusted service management. We introduce a trust-based message evaluation system, incorporating reputation assessment and negative feedback functions to evaluate the credibility of messages and assessments. A reward and punishment mechanism based on repeated games is designed to incentivize vehicles to proactively share information, thereby preventing false information and defamation attacks. Additionally, a blockchain-based distributed trust management scheme is designed to ensure the consistency of trust management storage through the consensus mechanism of the blockchain, reducing reliance on centralized institutions. Simulation results demonstrate that the establishment of reputation and incentive mechanisms among vehicles enhances the enthusiasm for information sharing and improves the accuracy of identifying false messages.