The article discusses the problem of front-running attacks on Ethereum, a type of security threat where malicious actors monitor other users’ transactions and then submit their own with higher fees to ensure precedence. The authors introduce a detection method named FRAD (Front-Running Attacks Detection on Ethereum using Ternary Classification Model), specifically designed for transactions within decentralized applications (DApps) on Ethereum. The method accurately classifies front-running attacks involving transaction displacement, insertion, and suppression. The research validates that the Multilayer Perceptron (MLP) classifier offers optimal performance in detecting these attacks, with an accuracy rate of 84.59% and F1-score of 84.60%.
Publication date: 24 Nov 2023
Project Page: https://arxiv.org/abs/2311.14514
Paper: https://arxiv.org/pdf/2311.14514
