XSema: A Novel Framework for Semantic Extraction of Cross-chain Transactions

TL;DR

Cross-chain interoperability creates semantic monitoring challenges for multi-chain transactions. The authors propose XSema, a two-module semantic extraction framework that models cross-chain transactions through asset transfer semantics and message-passing semantics, then fuses them for classification into cross-chain deposit $DT$, cross-chain withdrawal $WT$, or non-cross-chain $NT$ transactions. They construct the first cross-chain semantic extraction dataset (11,879 cross-chain pairs and 10,183 non-cross-chain) from 10 bridges and demonstrate that XSema achieves up to 99.72% generality accuracy and 94.81% generalizability, outperforming a MoTS baseline. A key insight is that cross-chain transactions exhibit concentrated motif distributions in the asset-transfer graph and distinctive event-logs terminology, offering new perspectives on cross-chain ecosystems. These results support improved cross-chain security monitoring and regulatory capabilities.

Abstract

As the number of blockchain platforms continues to grow, the independence of these networks poses challenges for transferring assets and information across chains. Cross-chain bridge technology has emerged to address this issue, establishing communication protocols to facilitate cross-chain interaction of assets and information, thereby enhancing user experience. However, the complexity of cross-chain transactions increases the difficulty of security regulation, rendering traditional single-chain detection methods inadequate for cross-chain scenarios. Therefore, understanding cross-chain transaction semantics is crucial, as it forms the foundation for cross-chain security detection tasks. Although there are existing methods for extracting transaction semantics specifically for single chains, these approaches often overlook the unique characteristics of cross-chain scenarios, limiting their applicability. This paper introduces XSema, a novel cross-chain semantic extraction framework grounded in asset transfer and message-passing, designed specifically for cross-chain contexts. Experimental results demonstrate that XSema effectively distinguishes between cross-chain and non-cross-chain transactions, surpassing existing methods by over 9% for the generality metric and over 10% for the generalization metric. Furthermore, we analyze the underlying asset transfer patterns and message-passing event logs associated with cross-chain transactions. We offer new insights into the coexistence of multiple blockchains and the cross-chain ecosystem.

Figures (7)

• Figure 1: Overview of XSema. The framework inputs the asset transfer graph and event log text, producing transaction types that include non-cross-chain, deposit, and withdrawal transactions.
• Figure 2: The components of cross-chain bridge.
• Figure 3: Asset Transfer Graph Modeling.
• Figure 4: Directed network motifs.
• Figure 5: Message-passing Text Modeling.