OpenAI is taking a deeper dive into cryptocurrency security with the launch of EVMbench, a new testing framework designed to measure how well artificial intelligence can understand and potentially secure smart contracts on Ethereum and similar blockchains.
Smart contracts, self-executing code deployed on blockchains such as Ethereum, power decentralized exchanges, lending protocols, and a wide range of on-chain financial applications. These contracts typically cannot be modified once deployed, making their vulnerabilities potentially serious.
EVMbench is OpenAI’s attempt to see if modern AI systems are doing their part to prevent these problems. The benchmark was built in collaboration with cryptocurrency investment firm Paradigm and leverages real-world smart contract vulnerabilities previously discovered through audits and security competitions.
The system measures performance across three key capabilities: identifying security bugs, exploiting those bugs in a controlled environment, and fixing vulnerable code without violating contracts.
OpenAI says its goal is to establish clear standards for evaluating AI systems in blockchain security, especially as decentralized finance continues to secure billions of dollars in user funds. The stakes for smart contracts are only going to increase.
“Smart contracts regularly secure more than $100 billion in open source crypto assets. As AI agents improve their ability to read, write, and execute code, it becomes increasingly important to measure that ability in economically meaningful environments and encourage the use of AI systems defensively to audit and enforce deployed contracts,” OpenAI said in a blog post.
Read more: Most Influential Person: Sam Altman
