Detecting unknown vulnerabilities in smart contracts with the CNN-BiLSTM model

Smart contracts, fundamental to blockchain technology, are extensively utilized in diverse fields such as finance, supply chain management, and beyond. Nevertheless, once deployed, their capability to handle significant transactions and their unchangeable nature bring about substantial risks, potentially leading to severe security breaches and financial losses. While existing research has made progress in detecting unknown vulnerabilities, identifying novel, unforeseen security issues remains significant. We aim to contribute to this ongoing effort by introducing an innovative approach that capitalizes on the similarities between known and unknown vulnerabilities. We propose a CNN-BiLSTM model meticulously designed to identify features of known vulnerabilities and employ them to detect potential unknown vulnerabilities. We intricately gather opcode sequences generated during smart contract execution using Geth instrumentation and meticulously analyze them. We conduct rigorous experiments to validate the model’s effectiveness in detecting potential unknown vulnerabilities. Our approach represents a step forward in blockchain security by providing proactive measures to strengthen smart contract security against emerging threats.