A novel hybrid feature fusion model for detecting phishing scam on Ethereum using deep neural network

作者：

Highlights：

• A more effective approach to extract features from transaction records.

• A model integrates manual feature engineering and transaction records analysing.

• Achieves high F1 on the phishing scam accounts detection on Ethereum.

• Outperforming the existing state-of-the-art methods.

摘要

•A more effective approach to extract features from transaction records.•A model integrates manual feature engineering and transaction records analysing.•Achieves high F1 on the phishing scam accounts detection on Ethereum.•Outperforming the existing state-of-the-art methods.

论文关键词：Blockchain,Ethereum,Phishing scams detection,Deep learning,LSTM-FCN,BP neural network

论文评审过程：Received 9 April 2022, Revised 7 July 2022, Accepted 5 August 2022, Available online 18 August 2022, Version of Record 1 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118463