Salus Gitbook
  • 😀Welcome to Salus!
  • 🧑‍⚕️Audit
    • Audit Overview
    • Auditing Scope (Solidity)
    • Vulnerabilities Description
    • Cases Study
      • ERC20
      • NFT
      • DeFi
      • Smart Contract Migration from Ethereum to Other Chains
  • 🕵️Web3 Penetration test
    • Web3 Penetration Test Overview
    • Risks in GameFi
    • Risks in DeFi
    • Risks in Cefi
    • Risks in social media
  • 🐱Lightning Cat
    • Lightning Cat Overview
    • Machine Learning
    • DOT Diagram
    • Formal Verification
    • Fuzzing Test
    • Let·s Get Started!
  • Common Question
    • 🖋️Common Question
      • 📪Audit Process
      • 💡What is Smart Contract Expert Audit?
      • ✨Why should you choose Salus for Expert Audit?
      • 🧠Why Salus is your best choise?
Powered by GitBook
On this page
  1. Lightning Cat

Machine Learning

PreviousLightning Cat OverviewNextDOT Diagram

Last updated 1 year ago

Salus Lightning Cat employs machine learning techniques for smart contract vulnerability detection. We have trained three deep learning models for detecting vulnerabilities in smart contracts: Optimized-CodeBERT, Optimized-LSTM, and Optimized-CNN. To accurately extract vulnerability features, we obtain code snippets from vulnerable functions, preserving key vulnerability characteristics. By leveraging the CodeBERT pre-trained model for data preprocessing, we can more accurately capture the syntax and semantics of the code, thereby improving the performance of vulnerability detection.

🐱