AmirhosseinHonardoust/How-AI-Detects-Rugpulls
A deep technical article exploring how AI, feature engineering, and static smart-contract analysis uncover rugpull risks before humans detect them. Covers Solidity pattern mining, mint abuse detection, blacklist/fee manipulation signals, ML-inspired scoring models, and how to quantify ERC-20 token scam probability.
This project helps cryptocurrency investors and blockchain security analysts identify potential 'rugpull' scams in ERC-20 tokens before they happen. It takes the Solidity smart contract code of a token and analyzes it for dangerous patterns, outputting an interpretable risk score and a label like 'safe' or 'rugpull_candidate'. This allows non-technical users to quickly assess the trustworthiness of a token.
Use this if you want to quickly screen ERC-20 token smart contracts for common scam risks and get a clear, interpretable risk score without needing to manually audit complex code.
Not ideal if you need to detect runtime exploits, liquidity issues, or complex multi-contract interactions, as this tool focuses solely on static analysis of a single token's code.
Stars
21
Forks
—
Language
—
License
MIT
Category
Last pushed
Nov 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/How-AI-Detects-Rugpulls"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sigp/blockprint
DEPRECATED block fingerprinting
scthornton/trylock
TRYLOCK is a layered security system that protects AI chatbots from manipulation attacks by...
edenia/tikuna
A P2P network security monitoring system for the Ethereum blockchain. :closed_lock_with_key:
rahulsnkr/UnBlockd
A deep learning security system with decentralized onboarding
AmirhosseinHonardoust/Onchain-Security-Suite
A complete Web3 security toolkit combining AI-powered token auditing, ML-based deployer...