2025 International Conference on Blockchain and Web3.0 Technology Innovation and Application Exchange

Table of Contents

1. Frontmatter

2. Protocols, Security, and Smart Contracts

   1. Frontmatter

   2. Zero-Shot Detection of Bytecode-Level Ponzi Contract Using LLM

      Zhenyong Xu, Tian Lan, Leyan Liu, Yihua Zhu, Ruiheng Zhang, Wei Chen

      Abstract

      Smart contracts on Ethereum have driven the development of decentralized financial applications, but they have also become a breeding ground for fraudulent activities, particularly Ponzi schemes. These schemes often obscure the flow of funds and the relationships among participants, making their true nature difficult to detect–especially when only the contract’s bytecode is publicly available. Conventional detection methods largely depend on access to source code or large-scale labeled datasets to train supervised learning models. However, in real-world blockchain environments, only compiled bytecode is typically accessible on-chain, and obtaining labeled data is costly and often impractical. To address this challenge, we propose a novel approach to identify Ponzi schemes directly from Ethereum bytecode, without relying on source code or labeled data. Under a zero-shot setting, we utilize large language models to interpret and assess critical code fragments extracted from the contract, aiming to judge whether their functionality matches typical Ponzi-like fund behaviors. Our method first decompiles the bytecode into an intermediate form that preserves key semantic information, then constructs a data flow graph to represent data dependencies and control flow relationships within the contract. Based on this graph, we apply a set of manually defined rules to locate and extract code segments that are strongly related to fund transfer logic. These segments are then provided to the language model for further reasoning and judgment. By integrating bytecode analysis with LLM-based interpretation, our method can detect suspicious fund flow patterns even when the original source code is not available.

   3. Smart Contract Vulnerability Detection Using Combined Sequence and Graph Features from Source Code

      Jinghui Fang, Zhihao Hou, Gansen Zhao, Kai Zheng

      Abstract

      Smart contract vulnerabilities represent a significant threat to the security and reliability of blockchain ecosystems, highlighting the need for efficient and accurate detection methods. Existing methods struggle to capture the rich semantic and structural information in smart contracts. To address these issues, this work proposes SeqGraphFusion (SGF), a framework that leverages the complementary strengths of token sequence and graph-based representations extracted from smart contract source code. SGF’s key insight lies in its heterogeneous fusion of these sequence and graph features, enabling a more comprehensive understanding of the contract. To enhance the modeling of long-range dependencies, which have been constrained in traditional Graph Neural Networks due to the nature of message passing, SGF incorporates a Graph Transformer-based architecture, facilitating more effective information propagation. The experimental results demonstrate that our method significantly outperforms existing approaches, achieving a notable improvement in the F1 score, with an average increase of 2.82% across arithmetic and reentrancy vulnerability detection tasks compared to the best-performing baseline. Specifically, our method achieves F1 scores of 92.26% and 95.1% for arithmetic and reentrancy vulnerabilities, respectively. By effectively harnessing the complementary strengths of token sequence and graph-based representations to form a more comprehensive model of smart contract code, this work establishes a valuable new technique that not only enhances smart contract security but also promotes the development of more robust blockchain applications.

   4. UAVSpectrumChain: Smart-Contract Based Credible Spectrum Trading for UAV Communications

      Muntasir Al Mamun, Qin Wang, Jiaying Qian, Li Gao

      Abstract

      Modern wireless networks and Unmanned Aerial Vehicles (UAVs) both grapple with one core challenge: spectrum scarcity. Yet, as UAVs promise on-demand coverage whether over busy city streets or remote rural areas traditional, centralized spectrum allocation schemes struggle to keep pace. In response, we present UAVSpectrumChain, a fully decentralized marketplace built on Ethereum smart contracts. In our system, ground users (from mobile devices to IoT gateways) register their spectrum needs and lock a small collateral deposit to guarantee honest bidding. Meanwhile, UAV operators specify their available bandwidth and tune their prices according to both revenue targets and a personal “satisfaction” parameter that reflects their own operational priorities. A single smart contract orchestrates four seamless phases Setup, Pricing, Allocation, and Completion automatically computing market-clearing prices, iteratively matching buyers and sellers until equilibrium is reached, and settling payments without human intervention. We implemented a Solidity prototype on the Sepolia testnet and observed consistent convergence within 5–7 rounds, with predictable gas consumption. A minimal web interface powered by MetaMask offers real-time bidding and transparent dashboards, while on-chain event logs provide an immutable audit trail. UAVSpectrumChain demonstrates how blockchain can foster fair, transparent, and fully automated spectrum trading paving the way for the next generation of UAV-enabled communications.

   5. Cryptocurrency Network Anomaly Detection Based on Time-Aware Channel Fusion Dynamic Graph Neural Network

      Yong Li, Qianyu Song, Runshuo Liu, Chao Li, Hua Duan, Qingtian Zeng

      Abstract

      With the development of blockchain technology and cryptocurrency systems, transaction behaviors in financial networks have become highly dynamic and exhibit complex evolutionary patterns. Therefore, how to effectively model and understand the dynamic behaviors of nodes in financial networks, so as to enable risk detection and behavior prediction, has become a focal point in current research. In this paper, we propose a Time-aware Channel Fusion Network (TCF-Net) for modeling dynamic evolution and performing link prediction in cryptocurrency transaction networks. Specifically, we employ a time-aware historical neighbor sampling mechanism to extract multimodal features from first-hop interactions, including node attributes, transaction edge features, temporal encodings, and co-occurrence-based neighbor interaction information. Subsequently, we integrate recurrent neural networks for temporal dependency modeling with a multilayer perceptron-based hybrid module to perform channel-wise feature interaction. Experiments conducted on two real-world Bitcoin transaction networks and two phishing detection datasets demonstrate the superiority of our approach in link prediction tasks, achieving notable gains in both expressiveness and robustness. These results highlight the potential of time-aware dynamic graph modeling to enhance blockchain security analytics and user behavior understanding in cryptocurrency networks. Our code is available at https://github.com/ly896/TCF-Net.

   6. HSTA: Ethereum Phishing Fraud Detection Model Based on Dynamic Graph Hybrid Spatio-Temporal Attention Mechanism

      Mingxu Chen, Runshuo Liu, Qianyu Song, Ge Song, Chao Li, Qingtian Zeng

      Abstract

      With the popularization of blockchain technology, phishing and fraud activities on platforms such as Ethereum have become increasingly rampant, posing a serious threat to the transaction security of the blockchain ecosystem. Existing detection methods struggle to capture the dynamic evolution of transaction networks and effectively integrate spatio-temporal features to uncovering complex fraud patterns. Therefore, in this paper, we propose a novel phishing fraud detection method using a Hybrid Spatio-Temporal Attention network (HSTA) to address this increasing problem. Specifically, we first construct the Ethereum transaction records as a continuous-time dynamic graph. Then, we introduce a hybrid spatio-temporal attention mechanism to dynamically capture complex network dependencies. Finally, we aggregate neighborhood information via multi-layer Transformer encoders to generate node embeddings with strong representation capabilities for the downstream phishing transaction chain prediction task. The experimental results on the real Ethereum phishing fraud dataset and two public datasets show that HSTA outperforms the existing baseline models in both transduction and inductive learning scenarios. These findings demonstrate the practical value and effectiveness of our proposed HSTA model in combating phishing fraud activities in blockchain environments. Our code can be obtained at https://github.com/cmx12138/HSTA.

   7. Semantic Interaction and Relation-Decoupled Heterogeneous Graph Structure Learning: Application to Smart Contracts

      Lichao Zhang, Chunhua Li, Ge Song, Nengfu Xie, Chao Li, Qingtian Zeng

      Abstract

      Smart contracts are increasingly targeted by deceptive behaviors and phishing attacks, posing serious security risks to blockchain systems. Due to the heterogeneous nature of contracts, accounts, and transactions, Heterogeneous Graph Neural Networks (HGNNs) are commonly used for smart contract detection. However, existing HGNNs often entangle node features with graph topology, leading to semantic interference in complex interactions. Additionally, noise from disguised invocations and asynchronous data further undermines model robustness. To address these issues, we propose Semantic Interaction and Relation-Decoupled Heterogeneous Graph Structure Learning (SRHGSL), a self-supervised heterogeneous graph structure learning framework that incorporates semantic interaction and relation decoupling. SRHGSL constructs meta-path-based subgraphs to isolate semantics, applies attention to capture relational diversity, and leverages triplet contrastive loss to align semantic and attribute views. Extensive experiments on real-world datasets show that SRHGSL outperforms state-of-the-art methods, demonstrating superior robustness and effectiveness in smart contract detection and broader applications. The code is publicly available at https://github.com/7A13/SRHGSL.

   8. Learning to Detect Smart Contract Vulnerabilities from Code Property Graph

      Qing Xue, Zhijie Zhong, SiCheng Hao, ZeWei Lin, WeiLi Chen, Jing Bian

      Abstract

      Smart contract vulnerability detection has been more and more important in recent years. By the economic nature of blockchain, the vulnerabilities in smart contracts may directly lead to large financial losses. A variety of detection methods have been proposed to detect vulnerabilities such as reentrancy and timestamp dependence. However, as the number of smart contracts rapidly increases, new forms of reentrancy vulnerability have been exploited to perform powerful attacks. Existing machine learning based detection methods build their model based on the traditional “callvalue” pattern to detect reentrancy. Thus they are not able to adapt to the newly emerged vulnerabilities. In this work, we take the first step into building a flexible and accurate machine learning model for detecting the newly emerged vulnerabilities such as the “callvalue-excluded” reentrancy. Based on a deep investigation into real-world smart contracts, we extract effective features from program syntax and semantics, i.e. customized code property graph. A detection model named Code Property Graph Neural Network (CPGNN) is proposed to detect vulnerabilities in smart contracts. The proposed method is evaluated on over 2,000 smart contracts and the experiment results show that CPGNN can achieve high efficiency in vulnerability detection problem while effectively improving the detection accuracy.

   9. SD-ATD: Semantic-Decoupling Contrastive Learning Model for Blockchain Abnormal Transaction Detection

      Zongren Guo, Chao Li, Ya Liu, Ge Song, Qingtian Zeng

      Abstract

      In blockchain abnormal transaction detection, supervised graph neural networks (GNNs) are constrained by the scarcity of labeled data, whereas graph contrastive learning confronts the distinctive challenge of topological coupling in blockchain transaction graphs—namely, dense capital flows induce strong inter-node correlations, which directly violate the key instance independence assumption on which contrastive learning relies. To address this, we propose an efficient boundary-aware model Semantic-Decoupling Contrastive Learning Model for Blockchain Abnormal Transaction Detection (SD-ATD). The model employs spectral clustering to uncover transaction pattern clusters, followed by node partitioning into multiple clusters. Subsequently, the central node of each cluster—selected based on topological centrality and semantic representativeness—is used to reconstruct the graph into a capital-flow subgraph, thereby alleviating topological dependencies through semantic decoupling. Then reconstruct each subgraph to obtain the disturbed graph for comparative learning. Extensive node classification and node clustering experiments conducted on five benchmark datasets and four baselines empirically validate the effectiveness of SD-ATD in capturing abnormal transactions. Furthermore, the method outperforms other existing methods. The code is available at https://github.com/guiei/SD_ATD.

   10. BFCSR: A Blockchain-Based Federated Learning Framework with Client Selection and Round-Based Training Scheme

       Zijie Zhao, Xing He, Xinyu Ruan, Chenpei Wang, Yuan Liu, Xiaohui Zhong, Yang Yue, Ruhui Ma, Jinshan Sun

       Abstract

       In this paper, we propose a blockchain-based federated learning framework with client selection and a round-based training scheme (BFCSR). The framework contains three modules to help federated learning achieve better performance. The blockchain module provides defenses against data tampering and single-point failure. The client selection module selects high-quality clients to participate in the training. The round-based training module puts a time threshold on the training time to reduce the clients’ waiting time, improving overall performance. Comparison experiments to several baselines and results show that our framework performs better in various experiment settings.

   11. A Learning Behavior Based Framework for Secure Personalised Blockchain Federated Learning

       Yifei Tang, Zhaohui Zhang, Qinyuan Liu

       Abstract

       Federated Learning (FL) is vulnerable to the introduction of poisoned attack, resulting in inaccurate predictions for specific inputs. Some existing defense aim to identify and remove potentially poisoned model updates. However, this can also incorrectly exclude a fraction of benign client updates. So we propose a framework based on learning behavior for secure personalised blockchain federated learning. Clients build a learning process model containing learning behavior and small number of samples before uploading the local model, the miner performs global aggregation based on process consistency and knowledge quality and builds a knowledge repository for each client. Each client’s knowledge repository contains samples provided by clients with consistent behavior. The samples in the knowledge repository are examined in conjunction with the local knowledge of the client to generate a personalised knowledge repository. Even if the global model is poisoned, due to the differences in the behavior of normal and malicious clients and the differences in the features of normal and poisoned samples, the normal repository does not contain the poisoned features, and the poisoned samples are regarded as anomalies by the normal clients by comparing them with the personalised knowledge repository. Experimental results show that our method has better defense results compared to BVFB, RLR, MultiKrum and Median algorithms, with attack success rate below 3% under multiple attack scenarios.

   12. MultiSCDetect: A Multi-objective Detection-Based Framework for Smart Contract Vulnerability Detection

       Jing Dai, Yan Ye, Gang Du, Dan Li

       Abstract

       Smart contracts, as core components of the blockchain ecosystem, have security properties that directly affect the sustainability and value of decentralized applications. However, existing vulnerability detection methods exhibit significant limitations in terms of detection dimensions, environmental adaptability, and scalability of verification, leading to key issues such as high omission rates for cross-contract attacks and persistently high false positive rates in dynamic scenarios. Therefore, this paper proposes a smart contract vulnerability detection framework based on multi-objective detection, named MultiSCDetect. We also introduce a novel concept of Vulnerability Candidate Snippets (VCS) to help the model capture critical points of vulnerabilities.MultiSCDetect can detect 12 types of vulnerabilities, including 10 widely recognized threats, and identifies additional unknown types through implicit features and a Multi-Objective Detection (MOD) algorithm without the need for expert knowledge or predefined rules. It supports the parallel detection of multiple vulnerabilities, offering high scalability without requiring a separate model to be trained for each type, thereby reducing significant time and human resource costs.MultiSCDetect is evaluated using more than 18,000 smart contracts on Ethereum. Experimental results show that it achieves an average F1-score of 94.8%, indicating strong detection performance.

   13. DDCTGAN: A Dual Discriminator Conditional Tabular Generative Adversarial Network for Network Intrusion Detection Systems

       Xinwei Hu, Wang Yan, Sheng Cao

       Abstract

       Network Intrusion Detection System (NIDS) is an important tool for ensuring network security and is widely used to defend against network attacks. Machine learning-based NIDS have demonstrated excellent performance in detecting attack traffic. However, there are issues: their detection accuracy drops when facing carefully designed adversarial attack traffic. Existing research shows that, to improve NIDS’ detection capability against adversarial attack traffic, more adversarial samples are needed for adversarial training to enhance the model’s robustness. However, the adversarial attack samples generated in current research are numeric, which presents two major limitations: 1) Numeric samples are inconsistent with the tabular data format commonly used in the NIDS field. Adversarial attack samples generated for one NIDS model will be incompatible with another NIDS model due to input format differences, resulting in poor generalization ability; 2) Numeric generation models are prone to excessively modify traffic features, causing the samples to no longer conform to network protocol specifications. To address these issues, we propose a Dual Discriminator Collaborative Optimization-based Tabular Data Generation Model (DDCTGAN). This model uses a dual discriminator mechanism to simultaneously learn the feature distribution of normal and attack samples, generating tabular adversarial attack samples that are consistent with the data format used in NIDS. The generated samples are more closely aligned with the original data distribution and provide more effective adversarial training for NIDS. Experimental validation: In the experimental section, the effectiveness of DDCTGAN is verified from two aspects: 1) the ability of adversarial attack samples to evade NIDS detection, and 2) the effect of using adversarial training samples to improve NIDS detection accuracy. The results show that the adversarial samples generated by DDCTGAN outperform the current state-of-the-art model, IDSGAN, in evasion rates; and NIDS retrained with adversarial attack samples generated by DDCTGAN performed better than IDSGAN in detection performance for DoS (90%) and Probe (95%) attack categories, with improvements over IDSGAN’s DoS (54.72%) and Probe (92.62%). Conclusion: In summary, DDCTGAN shows significant advantages in generating high-quality adversarial samples and enhancing NIDS robustness, providing a feasible solution for the effective detection of adversarial attack traffic in future NIDS applications.

   14. TrustZone-Based WebAssembly Smart Contract Execution for Privacy-Preserving Blockchain

       Xingyun Zheng, Jianrong Lu, Zhuoya Gu, Jianhai Chen

       Abstract

       With the rise of privacy-sensitive blockchain applications, traditional smart contracts’ transparency poses significant risks for sensitive data. We propose a lightweight execution architecture combining ARM TrustZone and WebAssembly to isolate contract logic in the Secure World, achieving hardware-level privacy while remaining compatible with standard blockchain frameworks. An efficient shared memory and extended WASI-based communication mechanism enables seamless cooperation between on-chain and trusted execution. We further implement a decentralized identity (DID) system supporting encrypted verifiable credential (VC) verification via ECDH key agreement and AES encryption. Experimental results show the system maintains low latency and high throughput for queries, transactions, and privacy verification, demonstrating the feasibility of deploying privacy-preserving smart contracts on mobile and edge devices.

   15. LogSentry: An LSTM-Based Framework for Real-Time Vulnerability Detection in Smart Contracts

       Lvbin Xu, Lei Wu, Xingyu Wu, Zhaoyu Su

       Abstract

       Smart contracts, as a core component of blockchain systems, play a critical role in ensuring the stability and trustworthiness of decentralized applications. The logs generated during contract execution provide essential evidence for vulnerability detection and behavior auditing. This paper proposes LogSentry, a deep neural network-based framework for real-time vulnerability detection in smart contracts. The framework leverages Long Short-Term Memory (LSTM) networks to model contract execution logs as natural language sequences, learning normal contract behavior patterns and promptly detecting log sequences that deviate from typical execution trajectories when potential anomalies occur. Furthermore, we introduce an incremental update mechanism that enables the model to dynamically adapt as contract log patterns evolve over time. Experimental results on multiple real-world smart contract datasets demonstrate that LogSentry achieves up to 97% accuracy in detecting abnormal executions and potential vulnerabilities, indicating its effectiveness and practical applicability.

   16. PROMISE: A Pedersen Commitment-Based Transaction Hiding Scheme for Blockchain System

       Zhengkang Fang, Jing Yu, Guangyue Huang, Rui Dong, Keke Gai

       Abstract

       Blockchain facilitates information exchange and financial trading. Blockchain public data accessibility compromises user transaction privacy. To address this problem, we propose a \(\underline{P}ede\underline{r}sen\, C\underline{o}mmitment-based\, Transaction\, Hiding\, Sche\underline{m}e\, for\, Blockcha\underline{i}n\, \underline{S}yst\underline{e}m\) (PROMISE). PROMISE utilizes the concealment and additive homomorphism of Pedersen commitments, integrated with Zero Knowledge Proof (ZKP) to realize amount hiding and confidential verification in transactions. Furthermore, PROMISE conceals transaction relationships through non interactive mixing and obfuscates user activity patterns via disguised transactions. Experimental evaluation shows that under high load conditions, PROMISE maintains transaction hiding while achieving a throughput rate of over 160 tps.