Advanced Approaches for Vulnerability Detection in Solidity-Based Smart Contracts: A Comparative Review

Abstract

With the advancement of blockchain technology, Solidity-based smart contracts have become essential for automating and securing digital transactions across various sectors, from finance to supply chain management. These contracts enable decentralized exchanges without intermediaries, enhancing transparency. However, their immutable nature poses security challenges: any flaw in the code becomes permanent, exposing contracts to attacks and leading to financial and reputational losses. This paper provides a comparative analysis of recent machine learning (ML) and deep learning (DL) techniques developed for detecting vulnerabilities in Solidity based smart contracts. By evaluating various approaches, we assess their effectiveness in identifying common threats such as reentrancy attacks and integer overflows. Finally, we highlight the importance of scalable, AI driven security solutions to address the growing complexity of vulnerabilities.