MetaTrust Labs, AgentLayer, and top academic institutions collaborate on research, receiving a prestigious academic conference award for pioneering breakthroughs in AI-enhanced smart contract security
Source: AgentLayer
San Diego, California - February 27, 2025 - The 32nd Network and Distributed System Security Symposium (NDSS 2025) has awarded its prestigious "Distinguished Paper Award" to the paper titled "PropertyGPT: LLM-Driven Smart Contract Formal Verification via Retrieval-Enhanced Property Generation." This groundbreaking research, conducted in collaboration between MetaTrust Labs and AgentLayer researchers and top academic institutions, introduces an innovative approach that utilizes a large language model (LLM) to automate and enhance the formal verification process.
PropertyGPT addresses a key gap in blockchain security by automatically creating comprehensive verification properties—an area that was previously a manual, expert-driven process. This technology has been successfully deployed through AgentLayer's decentralized AI network, marking a significant advancement in smart contract security practices.
"PropertyGPT not only addresses the efficiency bottlenecks of traditional formal verification but also achieves scalable applications through AgentLayer's distributed architecture," said Professor Liu Yang, Executive Director of the Nanyang Technological University Cyber Security Research Center in Singapore and co-founder of AgentLayer. "Our approach demonstrates that LLMs can significantly enhance the formal verification process, making it more accessible and comprehensive."
Technical Innovation and Impact
PropertyGPT leverages the contextual learning capabilities of state-of-the-art LLMs to transfer the knowledge of existing manually authored properties to custom security specifications generated for new smart contract code. The system incorporates various cutting-edge technologies:
- Retrieval-Enhanced Generation, combining LLM's semantic understanding with historical vulnerability data retrieval through a vector database
- Compiler and Static Analysis Feedback Loop to iteratively improve property quality
- Multi-dimensional Similarity Assessment for property ranking and selection
- Custom Prover for formal verification of properties
In extensive testing, PropertyGPT achieved an impressive 80% recall rate compared to expert-generated properties. The system successfully identified 26 known vulnerabilities out of 37 test cases and discovered 12 previously unknown security flaws, earning a $8,256 bug bounty reward.
AgentLayer Integration and Industry Impact
AgentLayer has integrated its proprietary AI Agent with PropertyGPT to optimize the automated verification process of smart contracts. Experiments have shown that this tool enhances vulnerability detection efficiency of complex contracts by 40% in DeFi and Web3 scenarios.
The NDSS Review Committee has praised this achievement as providing a "practically implementable paradigm upgrade for smart contract security."
Strategic Partnerships
The collaboration between MetaTrust Labs and AgentLayer represents a significant commitment to enhancing blockchain security through advanced AI technology. Future plans include:
- Launching cutting-edge AI products that combine MetaTrust Labs' expertise in smart contract security with AgentLayer's innovation in AI technology
- Developing specialized AI Agents for blockchain application development
- Building a more robust decentralized AI ecosystem
About the NDSS Symposium
Hosted by the Internet Society for over 30 years, the NDSS Symposium has evolved into one of the world's premier security conferences. Originally focused on network and distributed system security, the conference brings together hundreds of security educators, researchers, and practitioners from around the globe to advance the development of practical security technologies.
About the Research Team
The collaborative team includes researchers from MetaTrust Labs, AgentLayer, Singapore Management University, Hong Kong University of Science and Technology, and Nanyang Technological University: Ye Liu (SMU, AgentLayer), Yue Xue (MetaTrust Labs), Daoyuan Wu (HKUST, AgentLayer), Yuqiang Sun (NTU), Yi Li (NTU), Miaolei Shi (MetaTrust Labs), and Yang Liu (NTU, AgentLayer).
About MetaTrust Labs
MetaTrust Labs is a leading Web3 security platform that offers AI-driven solutions to blockchain developers. Born at Nanyang Technological University in Singapore, it provides tools for automated security scanning, smart contract auditing, and simplified security management. MetaTrust Labs is shaping the future of secure Web3 infrastructure.
About AgentLayer
AgentLayer is pioneering the future of decentralized AI with the launch of the world's first blockchain network designed for autonomous AI Agents. By seamlessly integrating cutting-edge AI capabilities with blockchain technology, AgentLayer enables developers and enterprises to massively build, deploy, and trade intelligent Agents.
You may also like
Morning Report | CoinEx becomes a key hub for Iran to evade sanctions, involving over $3.8 billion in funds; Kalshi seeks a new round of financing, with a valuation potentially rising to $40 billion
From the white-haired stock god to the billionaire fund mogul, the smart people shorting Nvidia are all getting rich using the same framework
Why do cryptocurrency projects always like to change their names?
Global Launch: As predictions become the most scarce asset in the AI era, Manadia is defining the next generation of the value internet
Who is footing the bill for the $64 billion accounting frenzy?
I never expected that the first application of AI x Crypto would be in security auditing
What is your view on Binance's competitive advantages?
ETH has entered a non-consensus phase, and the turning point is approaching!
The shift in the cloud of the air: from despising stablecoins a year ago to the high-profile entry of capital today
The survival dilemma of small and medium exchanges behind the withdrawal anomalies exposed by AscendEX
Why Is Bitcoin Falling Below $60K? 5 Key Market Drivers Explained
Bitcoin has dropped sharply amid ETF outflows, Strategy stock weakness, AI stock rallies, and changing Fed expectations. Explore the key forces driving BTC’s latest correction and what traders should watch next.
Bitcoin vs. Gold in 2026: Which Asset Performs Better in Different Markets?
Morning News | The draft amendment to the People's Bank of China Law aims to clarify the legal status of digital renminbi; South Korea will transfer about 40 unregistered virtual asset service providers to law enforcement agencies
The cryptocurrency industry has entered the "Show Me" era: merely relying on vision is no longer enough
Interpreting the Ethereum Foundation's new structure: Reaffirming self-sovereignty amid institutional trends
Former SpaceX engineer reconstructs the financial execution system using first principles
Standard Chartered Bank sings a 50x rhapsody again, aiming for AAVE to reach 3500 USD
Tidal Investment: We still have a positive outlook on the AI industry chain, but the reasons have changed
Morning Report | CoinEx becomes a key hub for Iran to evade sanctions, involving over $3.8 billion in funds; Kalshi seeks a new round of financing, with a valuation potentially rising to $40 billion
From the white-haired stock god to the billionaire fund mogul, the smart people shorting Nvidia are all getting rich using the same framework
Why do cryptocurrency projects always like to change their names?
Global Launch: As predictions become the most scarce asset in the AI era, Manadia is defining the next generation of the value internet
Who is footing the bill for the $64 billion accounting frenzy?
I never expected that the first application of AI x Crypto would be in security auditing
