With the rise of Web3, Non-Fungible Tokens (NFTs) have become a new class of digital assets, driving demand for large-scale NFT recommendation systems. Each NFT can be associated to a rich set of semantic, stylistic, and thematic labels, forming a highly complex label space. Similar to e-commerce platforms where detailed product labels enable personalized recommendations, such semantic dependencies between labels can potentially enhance NFT recommendation performance. Thus, NFT recommendation can be naturally formulated as an extreme multi-label (XML) classification problem. Many existing probabilistic label tree (PLT)-based approaches address XML problem by recursively partitioning the label space, which greatly alleviates the demands on expensive computer resources. Yet, the highly skewed distribution of labels in datasets in XML makes tail labels more challenging to predict than head labels. In this paper, Our preliminary analysis reveals that inherent label dependencies can be leveraged to improve tail label recommendations for NFTs. We propose ChainTail, a dependency-aware framework that enhances PLT-based NFT label partitioning and prediction re-scoring. It includes: (1) a Dependency-aware partition module that partitions highly dependent NFT labels into subsets. (2) a Dependency-aware ReScore module that re-ranks prediction scores of labels to eliminate the label-priors. Our experimental results show that ChainTail boosts tail label recommendation on widely used item recommendation datasets.
There is a lack of standardized datasets for NFT (Non-Fungible Token) recommendation systems. This study presents a comprehensive dataset designed for NFT recommendation systems, incorporating both NFT-related data (e.g., images, textual descriptions, rarity and transaction data) and user-related data (e.g., purchase price, transaction duration, and NFT holding period). To create the dataset, a Data Collection Tool was developed to gather raw data via the OpenSea API, and a Data Preparation Tool was implemented for preprocessing and filtering. All data used in this study are publicly available and anonymized, ensuring that user privacy is fully preserved. The dataset is evaluated using NFT-NCFAE, a deep learningbased NFT recommendation model, with performance measured by Recall and NDCG evaluation metrics. The evaluation results demonstrate the suitability and value of the proposed dataset for NFT recommendation systems. By making the dataset and its associated tools publicly available, this work aims to establish a benchmark for future research and enable comparability across different models.
With the rapid development of blockchain technology and the popularity of cryptocurrency, phishing scams pose an increasingly severe threat to the security of cryptocurrency transactions. Existing fraud detection methods have not accurately identified phishing behaviors, especially failing to capture key neighbor information and its impact effectively. To address this problem, we proposed a phishing detection framework based on FAAN-GBM (Feature and Attention Augmented Network with Gradient Boosting Machine), which aims to improve phishing fraud detection effectiveness on the Ethereum platform by further refining the extraction of phishing account features. This framework integrates basic features, transaction features, and interaction features of nodes, optimizes feature aggregation through importance analysis and attention mechanism of neighbor node, and uses autoencoders to deepen the nonlinear expression of node features. Through extensive testing on real Ethereum datasets, FAAN-GBM has demonstrated superior performance over existing methods, effectively improving the identification accuracy of phishing fraud nodes.
Phishing scams represent a significant criminal activity on Ethereum, driving the need for effective detection methods. The methods based on graph neural networks(GNNs) make significant breakthroughs due to their ability to model complex transaction networks. However, existing approaches often overlook the heterogeneity of Ethereum’s transaction graph during neighbor nodes aggregation. These methods typically focus on low-order neighbors, disregarding high-order ones, which limits their overall performance. To this end, we propose the High- and Low-order Transaction Aggregation Graph Network(HLTAG), which separately aggregates high- and low-order features for more effective feature representation. Specifically, we utilize biased random walk to aggregate low-order neighbors. We employ path aggregation to handle high-order neighbors. To mitigate the influence of noise and redundant information from high-order neighbors, we introduce a combination of attention decay, node similarity, and path attention mechanism, which dynamically adjust the aggregation weights. Extensive experiments demonstrate that HLTAG (94.4% Recall and 89.3% AUC) outperforms the state-of-the-art approaches in detecting Ethereum phishing scams, and exhibits significant advantages in large-scale scenarios.
Private information retrieval (PIR) over Web 3.0 introduces a sophisticated dimension to data access and privacy protection. It enables users to retrieve specific information from databases without disclosing the exact data being accessed. In decentralized networks, where privacy and data security are critical, PIR techniques play a pivotal role in safeguarding user confidentiality. By employing cryptographic protocols, PIR ensures that users can query decentralized databases while preserving anonymity and preventing unauthorized data interception. This chapter delves into the intricate mechanics of PIR algorithms tailored for Web 3.0 environments, exploring how these techniques facilitate secure information retrieval and uphold privacy standards amidst distributed ledger technologies and decentralized applications (dApps). It examines the integration of PIR within emerging decentralized search engines, highlighting the advancements and challenges in deploying privacy-preserving mechanisms across decentralized networks.
Cryptocurrency crime incidents in Ethereum are continuously rising, with phishing scams accounting for 50% of all criminal activities. The severe data imbalance significantly impacts the performance of Ethereum phishing detection models. The current solution may introduce redundant information or lead to the loss of important data. In this paper, we propose an Ethereum phishing detection method based on Graph Contrastive Learning with augmentations. This approach addresses the issue of insufficient learning of phishing node features, thus alleviating the influence of data imbalance on the model’s detection performance without disrupting the original data distribution. To enhance the representation of structural features, we employ two data augmentation methods: feature masking and edge perturbation. We conducted extensive experiments on a real Ethereum phishing dataset to evaluate the performance of our method. Compared to alternative methods, our approach not only significantly improves Precision, ranging from 12% to 30%, but also achieves noticeable enhancements in Recall, Auc, and F1-score. The experimental results provide ample evidence of the effectiveness of the proposed method.