一句话：提出 AtomGraph，用多模态 GCN 融合字节码 CFG 结构与操作码语义特征，自动检测智能合约原子性违反。
智能合约广泛部署于各类去中心化场景，原子性违反已成为其关键安全风险，而现有分析工具精度不足，难以有效检出此类问题。本文提出 AtomGraph——一个面向原子性违反检测的自动化框架，基于图卷积网络（GCN）进行多模态特征学习与融合。在协同学习机制驱动下，模型同时从两个异构模态中学习：一方面从基于字节码构建的控制流图（CFG）中提取结构化拓扑特征，另一方面从操作码序列中挖掘深层语义信息；并设计自适应加权融合机制，动态调整各模态特征权重以实现最优融合。最终由 GCN 在合约级别完成原子性违反的图级判定。实验评估表明，AtomGraph 达到 96.88% 的准确率与 96.97% 的 F1 分数，优于现有工具；相比采用拼接融合的基线模型，F1 分数提升 6.4%，显示出其在智能合约安全检测中的应用潜力。
Smart contracts are a core component of blockchain technology and are widely deployed across various decentralized scenarios. However, atomicity violations have become a critical potential security risk. Existing analysis tools often lack the precision required to detect these issues effectively. To address this challenge, we introduce AtomGraph, an automated framework designed for detecting atomicity violations. This framework leverages Graph Convolutional Networks (GCN) to accurately identify atomicity violations through multimodal feature learning and fusion. Specifically, driven by a collaborative learning mechanism, the model simultaneously learns from two heterogeneous modalities: extracting structural topological features from the bytecode-based Control Flow Graph (CFG) and uncovering deep semantics from its opcode sequence. We designed an adaptive weighted fusion mechanism to dynamically adjust the weights of features from each modality to achieve optimal feature fusion. Finally, GCN detects graph-level atomicity violations on the contract. Comprehensive experimental evaluations demonstrate that AtomGraph achieves 96.88% accuracy and 96.97% F1 score, outperforming existing tools. Furthermore, compared to the baseline concatenation fusion model, AtomGraph improves the F1 score by 6.4%, proving its potential in smart contract security detection.
@inproceedings{paperbot11986,
title = {AtomGraph: Tackling Atomicity Violation in Smart Contracts using Multimodal GCNs},
author = {Xiaoqi Li and Zongwei Li and Wenkai Li and Zeng Zhang and Lei Xie},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786582.3786816}
}