Semantic Sleuth: Identifying Ponzi Contracts via Large Language Models
This program is tentative and subject to change.
Smart contracts, self-executing contracts with the terms of the agreement directly written into code, have become integral to blockchain technology, particularly in decentralized finance and Web3. The prevalence of Ponzi schemes in smart contracts poses a significant scam, causing substantial financial losses and undermining trust in blockchain-based systems. Existing detection methods heavily rely on large amounts of labeled data and static information, resulting in poor reliability and the inability to detect unseen Ponzi schemes. In this paper, we propose PonziSleuth, the first LLM-driven method for detecting Ponzi smart contracts. PonziSleuth leverages the advanced language understanding capabilities of LLMs to analyze smart contract source code directly, using a novel two-step zero-shot chain-of-thought prompting technique. We conducted a comprehensive performance evaluation using widely adopted benchmark datasets and real-world smart contracts. Our results demonstrate that PonziSleuth significantly outperforms state-of-the-art detection methods, achieving high accuracy and reliability. Specifically, PonziSleuth achieved a balanced detection accuracy of 96.06% with GPT-3.5-turbo, 93.91% with LLAMA3, and 94.27% with Mistral, showcasing its superior performance over existing models. In real-world detection, PonziSleuth effectively identified 15 new Ponzi schemes from 4,597 contracts verified by Etherscan in Mar 14-24, 2024, achieving a false negative rate of 0% and a false positive rate of 0.29%. We believe PonziSleuth represents a significant step in leveraging LLMs for mitigating scams and enhancing blockchain security.
This program is tentative and subject to change.
Thu 31 OctDisplayed time zone: Pacific Time (US & Canada) change
15:30 - 16:30 | Smart contract and block chain 2NIER Track / Research Papers / Tool Demonstrations at Camellia Chair(s): Vladimir Filkov University of California at Davis, USA | ||
15:30 15mTalk | Semantic Sleuth: Identifying Ponzi Contracts via Large Language Models Research Papers Cong Wu The University of Hong Kong, Jing Chen Wuhan University, Ziwei Wang Wuhan University, Ruichao Liang Wuhan University, Ruiying Du Wuhan University | ||
15:45 15mTalk | AdvSCanner: Generating Adversarial Smart Contracts to Exploit Reentrancy Vulnerabilities Using LLM and Static Analysis Research Papers Yin Wu Xi'an Jiaotong University, Xiaofei Xie Singapore Management University, Chenyang Peng Xi'an Jiaotong University, Dijun Liu Ant Group, Hao Wu Xi'an JiaoTong University, Ming Fan Xi'an Jiaotong University, Ting Liu Xi'an Jiaotong University, Haijun Wang Xi’an Jiaotong University | ||
16:00 10mTalk | ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts Tool Demonstrations Che Wang Peking University, China, Jiashuo Zhang Peking University, China, Jianbo Gao Beijing Jiaotong University, Libin Xia Peking University, Zhi Guan Peking University, Zhong Chen | ||
16:10 10mTalk | HighGuard: Cross-Chain Business Logic Monitoring of Smart Contracts Tool Demonstrations Mojtaba Eshghie KTH Royal Institute of Technology, Cyrille Artho KTH Royal Institute of Technology, Sweden, Hans Stammler KTH Royal Institute of Technology, Wolfgang Ahrendt Chalmers University of Technology, Thomas T. Hildebrandt University of Copenhagen, Gerardo Schneider University of Gothenburg | ||
16:20 10mTalk | Oracle-Guided Vulnerability Diversity and Exploit Synthesis of Smart Contracts Using LLMs NIER Track Mojtaba Eshghie KTH Royal Institute of Technology, Cyrille Artho KTH Royal Institute of Technology, Sweden |