Blockchain Smart Contract Vulnerability Detection and Segmentation Using ML

Abstract

Detecting vulnerabilities in smart contracts presents a significant challenge due to the unique nature of the vulnerabilities and the complexity of contract codes [3]. Existing approaches, which include formal verification, symbolic execution, machine learning (ML), and deep learning (DL), often struggle with issues of accuracy, transparency, and the ability to adapt to new threats [6]. This research introduces an innovative system that employs graph-based feature extraction alongside ML-based prediction to improve the identification of vulnerabilities in Ethereum smart contracts [1].