Blockchain networks are critical for safeguarding digital transactions and assets, but they are increasingly targeted by ransomware attacks exploiting zero-day vulnerabilities. Traditional detection techniques struggle due to the complexity of these exploits and the lack of comprehensive datasets. The UGRansome dataset addresses this gap by offering detailed features for analysing ransomware and zero-day attacks, including timestamps, attack types, protocols, network flows, and financial impacts in bitcoins (BTC). This study uses the Lazy Predict library to automate machine learning (ML) on the UGRansome dataset. The study aims to enhance blockchain security through ransomware detection based on zero-day exploit recognition using the UGRansome dataset. Lazy Predict streamlines different ML model comparisons and identifies effective algorithms for threat detection. Key features such as timestamps, protocols, and financial data are used to predict anomalies as zero-day threats and to classify known signatures as ransomware. Results demonstrate that ML can significantly improve cybersecurity in blockchain environments. The DecisionTreeClassifier and ExtraTreeClassifier, with their high performance and low training times, are ideal candidates for deployment in real-time threat detection systems.

翻译：区块链网络对于保护数字交易与资产至关重要，但其正日益成为利用零日漏洞的勒索软件攻击的目标。传统检测技术因这些攻击的复杂性及缺乏全面数据集而面临挑战。UGRansome数据集通过提供用于分析勒索软件与零日攻击的详细特征填补了这一空白，包括时间戳、攻击类型、协议、网络流以及比特币（BTC）财务影响。本研究利用Lazy Predict库对UGRansome数据集进行自动化机器学习（ML）。研究旨在基于UGRansome数据集，通过零日漏洞利用识别的勒索软件检测来增强区块链安全性。Lazy Predict简化了不同ML模型的比较过程，并识别出用于威胁检测的有效算法。时间戳、协议和财务数据等关键特征被用于预测异常作为零日威胁，并将已知特征分类为勒索软件。结果表明，ML能显著提升区块链环境中的网络安全防护能力。其中DecisionTreeClassifier与ExtraTreeClassifier凭借其高性能与低训练时间，成为实时威胁检测系统部署的理想候选模型。