OpenAI and Paradigm Launch EVMbench to Explore AI Agent Applications in Smart Contract Security

Odaily News: OpenAI and crypto investment firm Paradigm have announced a collaboration to launch EVMbench, designed to evaluate the capabilities of AI Agents in the field of smart contract security, including identifying, patching, and exploiting high-risk vulnerabilities.

Both parties stated that as AI's capabilities in code writing and execution improve, it can be exploited by attackers but can also serve as a defensive tool. Therefore, it is necessary to test the security capabilities of AI systems in environments with real economic significance. EVMbench will provide various testing modes, including vulnerability detection, contract modification, exploitability elimination, and simulating complete attack processes in a sandboxed chain environment.

The launch of this tool comes as DeFi protocol Moonwell and cross-chain liquidity protocol CrossCurve recently suffered smart contract vulnerability attacks, raising concerns about AI-assisted code security. EVMbench is reportedly built on a selection of 120 vulnerability samples, covering multiple public audit and competition cases.

Industry analysis suggests that with advancements in AI technology, the barrier to identifying smart contract vulnerabilities may further decrease, accelerating the evolution of the contest between security defense and offensive capabilities.