With the escalating prevalence of malicious activities exploiting vulnerabilities in blockchain systems, there is an urgent requirement for robust attack detection mechanisms. To address this challenge, this paper presents a novel collaborative learning framework designed to detect attacks in blockchain transactions and smart contracts by analyzing transaction features. Our framework exhibits the capability to classify various types of blockchain attacks, including intricate attacks at the machine code level (e.g., injecting malicious codes to withdraw coins from users unlawfully), which typically necessitate significant time and security expertise to detect. To achieve that, the proposed framework incorporates a unique tool that transforms transaction features into visual representations, facilitating efficient analysis and classification of low-level machine codes. Furthermore, we propose a customized collaborative learning model to enable real-time detection of diverse attack types at distributed mining nodes. In order to create a comprehensive dataset, we deploy a pilot system based on a private Ethereum network and conduct multiple attack scenarios. To the best of our knowledge, our dataset is the most comprehensive and diverse collection of transactions and smart contracts synthesized in a laboratory for cyberattack detection in blockchain systems. Our framework achieves a detection accuracy of approximately 94\% through extensive simulations and real-time experiments with a throughput of over 1,100 transactions per second. These compelling results validate the efficacy of our framework and showcase its adaptability in addressing real-world cyberattack scenarios.

翻译：随着恶意活动利用区块链系统漏洞的现象日益频发，迫切需要鲁棒的攻击检测机制。为解决这一挑战，本文提出了一种新型协作学习框架，通过分析交易特征来检测区块链交易与智能合约中的攻击行为。我们的框架能够分类多种类型的区块链攻击，包括机器码级别的复杂攻击（例如注入恶意代码非法提取用户资产），这类攻击通常需要大量时间和安全专业知识才能检测。为实现此目标，该框架整合了一个独特工具，可将交易特征转化为视觉表征，从而促进低级机器码的高效分析与分类。此外，我们提出了一种定制化协作学习模型，使分布式挖矿节点能够实时检测不同类型的攻击。为构建综合性数据集，我们基于私有以太坊网络部署了试点系统，并实施了多种攻击场景。据我们所知，本数据集是在实验室环境下为区块链系统网络攻击检测合成的最全面、最多样化的交易与智能合约集合。通过大量仿真与实时实验，我们的框架在吞吐量超过每秒1100笔交易的情况下实现了约94%的检测准确率。这些令人信服的结果验证了框架的有效性，并展示了其在应对现实网络攻击场景中的适应性。