Odaily Planet Daily reports that OpenAI and the crypto investment firm Paradigm have announced a collaboration to launch EVMbench, a tool for evaluating AI agents’ capabilities in the field of smart contract security, including identifying, patching, and exploiting high-risk vulnerabilities.
Both parties stated that as AI’s abilities in coding and execution improve, it could be exploited by attackers or become a defensive tool. Therefore, it is necessary to test the security capabilities of AI systems in environments with real economic significance. EVMbench will offer multiple testing modes, including vulnerability detection, contract modification, elimination of exploitability, and full attack simulation in a sandbox chain environment.
Coinciding with the launch of this tool, 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 based on 120 selected vulnerability samples, covering various public audits and competition cases.
Industry analysts believe that with advances in AI technology, the threshold for identifying smart contract vulnerabilities may further decrease, and the game between security defense and attack capabilities is accelerating.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
CertiK: In March, it recorded 46 security incidents, with total losses of about $39.8 million
CertiK reports that in March 2026 there were 46 security incidents, with total losses of approximately $39.8 million, the highest monthly number since November 2024. Security incidents increased in the fourth quarter of 2025 and the first quarter of 2026, and the occurrence of code vulnerability exploits is linked to the rise of artificial intelligence.
GateNews6h ago
ZachXBT: Circle’s compliance enforcement has been inadequate; multiple security incidents involve amounts exceeding $420 million
On-chain investigator ZachXBT published a report stating that since 2022, Circle has repeatedly failed to properly carry out compliance in multiple incidents involving illegal funds, with amounts totaling more than $420 million. The report notes that in several security incidents, Circle did not freeze suspicious accounts in a timely manner, leading to severe losses. Despite having relevant mechanisms, Circle responded slowly when facing attacks and investigations into money laundering, which affected industry security.
GateNews8h ago
Here's what 'cracking' bitcoin in 9 minutes by quantum computers actually means
Google's Quantum AI team said earlier this week that a future quantum computer could derive a bitcoin private key from a public key in roughly nine minutes. The number ricocheted across social media and spooked markets.
But, what does it actually mean in practice?
Let's start with how bitcoin
CoinDesk19h ago
Japan’s Financial Services Agency Issues a Network Security Reinforcement Policy for Crypto Asset Exchange Businesses
The Japan Financial Services Agency has issued “Policy Guidelines for Strengthening Cybersecurity for Crypto Asset Exchange Businesses and Related Entities,” with the aim of strengthening investor asset protection. It proposes a three-layer security framework to address the new landscape of cyberattacks. In subsequent plans, it will conduct penetration testing on major operators and revise the guidance to raise security standards.
GateNews20h ago
HypurrFi is suspected to have suffered a domain hijacking incident; the project team urges users to pause using the official website
DeFi lending protocol HypurrFi issues a security warning, saying that its website domain has been compromised. It urges users not to use that domain and to pause interactions. The team confirms users’ funds are safe and is investigating the domain hijacking incident.
GateNews23h ago
Elon Musk's X to Auto-Lock Accounts Posting Crypto for First Time
X is implementing a new feature that auto-locks accounts with their first crypto post to combat phishing attacks. This aims to reduce the misuse of hijacked accounts for scams while enhancing user security.
Coinpedia04-03 17:37
