WZWenyin Zhang

Wenyin Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wenyin Zhang has a total of 106 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Continuous Test-Time Adaptation Method for Dynamic Haze Removal

    by Ye Liu, Zhen Wang, Yongli Chen, Xing Wang, Wenyin Zhang

  • CGCN-DF: A Cascade GCN Vulnerability Detection Framework for Secure CIoT Smart Contracts

    by Keqing Wang, Wenyin Zhang, Mengru Tu, Weihao Su

    With the widespread use of smart contracts in blockchain applications, particularly in the consumer Internet of Things (CIoT), the security of smart contracts has become increasingly critical. CIoT refers to an IoT environment where various consumer devices are intelligently connected and interact via the internet. In this context, smart contracts are frequently used to automate tasks such as device control, data sharing, and transaction verification. However, vulnerabilities in smart contracts can lead to system attacks, thereby compromising the security of the entire IoT network. The Cascade Graph Convolutional Network-based Vulnerability Detection Framework for smart contracts (CGCN-DF) proposed in this study effectively enhances the security assessment of smart contracts in CIoT applications. Devices and systems in CIoT environments typically exhibit high heterogeneity and complex interaction patterns, but a single graph structure cannot fully capture the multidimensional behavioral features and complex structural relationships of smart contracts. To address this issue, this paper introduces the Semantic Contract Graph (SCG), which integrates three graph representations—Abstract Syntax Tree (AST), Control Flow Graph (CFG), and Data Flow Graph (DFG)—into a unified graph structure, comprehensively covering different aspects of the code. Furthermore, as smart contracts in CIoT environments often involve real-time data flows and complex execution paths, the CGCN-DF framework employs a cascading mechanism that performs three-level graph convolutional processing through relational, Meta-path structures, and cyclic structures. This approach extracts rich and complementary information from multi-level features, explicitly models the dynamic interactions among syntax, execution paths, and data flows, and enhances the model’s contextual awareness of vulnerability-triggering conditions. Ultimately, the framework achieves coarse-grained detection at the contract level and fine-grained detection at the line level. Experimental results demonstrate that the proposed method can effectively localize vulnerabilities down to specific code lines. This not only enhances the precision and practicality of smart contract vulnerability detection but, more importantly, contributes an innovative technical framework and theoretical methodology to the CIoT field—particularly in areas such as DSL program analysis and the intersection of IoT and blockchain security. This work thereby helps advance the field toward more refined and context-aware security analysis aligned with the realistic characteristics of complex systems.

  • SPMNet: A Siamese Pyramid Mamba Network for Very-High-Resolution Remote Sensing Change Detection

    by Jiashu Wang, Jinze Song, Hao Zhang, Zekai Zhang, Yunlong Ji, Wenyin Zhang, Jinglin Zhang, Xing Wang

    Very-High-Resolution (VHR) remote sensing images are characterized by extremely high spatial resolution, incorporating higher pixel density and larger image sizes, which pose challenges for existing methods to extract complex texture features. Furthermore, due to the wide-area and high-resolution imaging strategy, VHR change detection images suffer from a severe imbalance between change pixels and non-change pixels, increasing the difficulty of handling change detection tasks. To address these challenges, we introduced the Omnidirectional Selective Scan Module (OSSM), which has the capability to process long sequences. By integrating it with the lightweight Siamese Feature Pyramid Network (SFPN), we designed a hybrid CNN-Mamba backbone, referred to as SPMamba. This backbone captures both global and local information within bitemporal feature maps at each stage, enhancing the precision of texture feature extraction. Additionally, to integrate the semantic features from each branch in SPMamba and reduce noise interference from non-target change areas, we developed a Hybrid Fusion Module (HFM). The HFM consists of two fusion modules: the High-Low Channel Fusion Module (HLM) and the Bilateral Channel Fusion Module (BCM), which facilitates both feature-level and channel-level integration, enhancing the sensitivity of the model to subtle changes. Extensive experimental results demonstrate that SPMNet achieves the highest F1-score of 91.80%, 90.99%, and 96.04% on the WHU-CD, LEVIR-CD, and CDD-CD datasets, respectively, outperforming eleven state-of- the-art methods. Moreover, the effects of varying image sizes on model training are thoroughly analyzed.


  • Open Access

    VulnScan GPT: a new framework for smart contract vulnerability detection combining vector database and GPT model

    by Lianjie Wang, Yunhao Zhao, Keqing Wang, Zhongwen Zhang, Wenyin Zhang

    With the rapid development of blockchain technology and smart contracts, the security issues of smart contracts have become increasingly serious. To address the significant limitations of traditional detection methods in handling the complexity and scale of smart contracts, a new framework for smart contract vulnerability detection that combines a vector database and a generative pre-trained transformer (GPT) model — VulnScan GPT — has been proposed. This framework comprises three main components: function signature extraction, vector database storage and retrieval, and GPT-based vulnerability detection. The framework uses the solc tool to generate an abstract syntax tree from smart contracts, extract function signatures, and vectorize the code for storage. By integrating the GPT model, the framework can preliminarily analyze and filter key functions based on common vulnerability scenarios and then retrieve relevant implementations from the vector database for in-depth assessment. This method gradually optimizes function analysis through an iterative detection mechanism, leveraging the efficient storage and retrieval capabilities of the vector database, combined with the deep natural language processing abilities of the GPT model, enhancing the accuracy and comprehensiveness of vulnerability detection. In the experimental evaluation, tests were conducted on various datasets to detect automated market maker price manipulation and initial risk deposit vulnerabilities, demonstrating that VulnScan GPT not only improves the accuracy of vulnerability detection, but also significantly reduces operational costs by optimizing token usage, resulting in an efficient and cost-effective detection solution.


  • Pocket convolution Mamba for brain tumor segmentation

    by Hao Zhang, Jiashu Wang, Yunhao Zhao, Lianjie Wang, Wenyin Zhang, Yeh-Cheng Chen, Neal Xiong


  • Open Access

    An Enhanced-Segmentation Assisted Framework for Oracle Bone Rubbings Recognition

    by Tong Wang, Defu Ding, Wenyin Zhang, Guangyuan Pan

    Oracle bone inscriptions are the earliest mature writing system in China. Research on the character recognition of oracle bone inscriptions is of great significance for interpreting ancient history and culture. However, current detection models have high requirements for topology datasets and are cumbersome to manually label. To address these issues, this study proposes an enhanced segmentation assisted framework for processing and recognizing oracle bone rubbings, integrating advanced image processing techniques and deep learning algorithms. The framework includes the YOLOv8-IE model for image segmentation, achieving an [email protected] of 0.945 and an [email protected] of 0.644, and the MobileViT-IE model for character recognition, achieving the final recognition accuracy of 0.9335. Experimental results show that the proposed framework effectively achieves automatic single-character segmentation and recognition of oracle bone inscriptions, demonstrating significant practical application value.

  • FRFT Domain Watermarking Algorithm Based on GA Adaptive Optimization

    by Qiaoqiao Du, Yanchen Zhao, Weijie Hao, Wenyin Zhang

  • Open Access

    Pocket Convolution Mamba for Brain Tumor Segmentation

    by Hao Zhang, Yunhao Zhao, Lianjie Wang, Jiashu Wang, Wenyin Zhang, Yeh-Cheng Chen, Neal Xiong

    In the field of brain tumor segmentation, models based on CNNs and Transformer have received a lot of attention. However, CNNs have limitations in long-range modeling, and although Transformers can model at long distances, they have quadratic computational complexity. Recently, State Space Models (SSM), exemplified by the Mamba model, can achieve linear computational complexity and are adept at long-distance interactions. In this paper, we propose Pocket Convolution Mamba (P-BTS), which utilizes the PocketNet paradigm, SSM, and patch contrastive learning to achieve an efficient segmentation model. Specifically, the encoder follows the PocketNet paradigm, the SSM is used at the highest level of the model encoder to capture rich semantic information, and patch contrastive learning is achieved through the results of dual-stream data. Meanwhile, we designed a Spatial Channel Attention (SCA) module to enhance control over spatial channels, and a Feature Complement Module (FCM) to facilitate the interaction between low-level features and high-level semantic information. We conducted comprehensive experiments on the BraTS2018 and BraTS2019 datasets, and the results show that P-BTS has excellent segmentation performance.