Dynamic Vulnerability Detection on Smart Contracts Using Machine Learning

TL;DR

This paper introduces Dynamit, a machine learning-based framework that detects reentrancy vulnerabilities in Ethereum smart contracts using only blockchain transaction and balance data, without needing code analysis or special environments.

Contribution

Dynamit is the first framework to detect reentrancy vulnerabilities using only transaction metadata and balance data, eliminating the need for domain knowledge or code instrumentation.

Findings

Successfully identifies vulnerable contracts with high accuracy

Provides execution traces that reproduce attacks

Operates solely on blockchain transaction data

Abstract

In this work we propose Dynamit, a monitoring framework to detect reentrancy vulnerabilities in Ethereum smart contracts. The novelty of our framework is that it relies only on transaction metadata and balance data from the blockchain system; our approach requires no domain knowledge, code instrumentation, or special execution environment. Dynamit extracts features from transaction data and uses a machine learning model to classify transactions as benign or harmful. Therefore, not only can we find the contracts that are vulnerable to reentrancy attacks, but we also get an execution trace that reproduces the attack.