Hybrid Active Learning Framework for Improved Detection of Blockchain Sandwich Attacks Using Automated Machine Learning and Mechanism Design Game Theory

Abstract

Blockchain technology has gained significant attention due to its decentralized and transparent nature, making it an attractive platform for various applications, including cryptocurrency transactions. However, the increasing adoption of blockchain technology has also attracted malicious actors seeking to exploit vulnerabilities in its security protocols. One such attack, known as the blockchain sandwich attack, poses a significant threat to the integrity and reliability of blockchain networks. In this paper, we propose a hybrid active learning framework leveraging automated machine learning (AutoML) and mechanism design game theory to enhance the detection of blockchain sandwich attacks. Our framework aims to improve the efficiency and accuracy of detection while minimizing false positives and negatives. We present experimental results demonstrating the effectiveness of our approach compared to existing methods, highlighting its potential to enhance the security of blockchain networks.