Phishing Detection in Blockchain Transaction Networks Using Ensemble Learning

The recent progress in blockchain and wireless communication infrastructures has paved the way for creating blockchain-based systems that protect data integrity enable secure information sharing. Despite these advancements, concerns regarding security privacy continue to impede widespread adoption of technology, especially when sharing sensitive data. Specific attacks against blockchains, such as poisoning attacks, leaks, a single point failure, must be addressed develop efficient blockchain-supported IT infrastructures. This study proposes use deep learning methods, including Long Short-Term Memory (LSTM), Bi-directional LSTM (Bi-LSTM), convolutional neural network (CNN-LSTM), detect phishing transaction network. These methods were evaluated on dataset comprising malicious benign addresses from Ethereum dark list whitelist dataset, results showed an accuracy 99.72%.