LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts
Decentralized Finance (DeFi) incidents stemming from the exploitation of smart contract vulnerabilities have culminated in financial damages exceeding $3 billion US dollars. Existing defense mechanisms typically focus on detecting and reacting to malicious transactions executed by attackers that target victim contracts. However, with the emergence of private transaction pools where transactions are sent directly to miners without first appearing in public mempools, current detection tools face significant challenges in identifying attack activities effectively.
Based on the fact that most attack logic rely on deploying one or more intermediate smart contracts as supporting components to the exploitation of victim contracts, in this paper, we propose a new direction for detecting DeFi attacks that focuses on identifying adversarial contracts instead of adversarial transactions. Our approach allows us to leverage common attack patterns, code semantics and intrinsic characteristics found in malicious smart contracts to build the LookAhead system based on Machine Learning (ML) classifiers and a transformer model that is able to effectively distinguish adversarial contracts from benign ones, and make just-in-time predictions of potential zero-day attacks. Our contributions are three-fold: First, we construct a comprehensive dataset consisting of features extracted and constructed from 210,643 recent contracts and 375 hand-picked then carefully reviewed and identified adversarial contracts deployed on the Ethereum and Binance Smart Chain (BSC) blockchains. Secondly, we design a condensed representation of smart contract programs called Pruned Semantic-Control Flow Tokenization (PSCFT) and use it to train a combination of ML models that understand the behaviour of malicious codes based on function calls, control flows and other pattern-conforming features. Lastly, we provide the complete implementation of LookAhead and the evaluation of its performance metrics for detecting adversarial contracts. Our experiments show that LookAhead achieves an F1-score as high as 0.8966, which represents an improvement of over 44.4% compared to the previous state-of-the-art solution Forta, with a False Positive Rate (FPR) at only 0.16%.
Tue 24 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
10:30 - 12:20 | Blockchain and Smart ContractIdeas, Visions and Reflections / Research Papers at Vega Chair(s): Cuiyun Gao Harbin Institute of Technology, Shenzhen | ||
10:30 10mTalk | SmartShift: A Secure and Efficient Approach to Smart Contract Migration Ideas, Visions and Reflections Tahrim Hossain Syracuse University, Faisal Haque Bappy Syracuse University, Tarannum Shaila Zaman University of Maryland Baltimore County, Raiful Hasan Kent State University, Tariqul Islam Syracuse University | ||
10:40 20mTalk | LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts Research Papers Shoupeng Ren Zhejiang University, Lipeng He University of Waterloo, Tianyu Tu Zhejiang University, Di Wu Zhejiang University, Jian Liu Zhejiang University, Kui Ren Zhejiang University, Chun Chen Zhejiang University DOI Pre-print | ||
11:00 20mTalk | SmartShot: Hunt Hidden Vulnerabilities in Smart Contracts using Mutable Snapshots Research Papers Ruichao Liang Wuhan University, Jing Chen Wuhan University, Ruochen Cao Wuhan University, Kun He Wuhan University, Ruiying Du Wuhan University, Shuhua Li Wuhan University, Zheng Lin University of Hong Kong, Cong Wu Wuhan University DOI | ||
11:20 20mTalk | Automated and Accurate Token Transfer Identification and Its Applications in Cryptocurrency Security Research Papers Shuwei Song University of Electronic Science and Technology of China, Ting Chen University of Electronic Science and Technology of China, Ao Qiao University of Electronic Science and Technology of China, Xiapu Luo Hong Kong Polytechnic University, Leqing Wang University of Electronic Science and Technology of China, Zheyuan He University of Electronic Science and Technology of China, Ting Wang Penn State University, Xiaodong Lin University of Guelph, Peng He University of Electronic Science and Technology of China, Wensheng Zhang University of Electronic Science and Technology of China, Xiaosong Zhang University of Electronic Science and Technology of China DOI | ||
11:40 20mTalk | Detecting Smart Contract State-Inconsistency Bugs via Flow Divergence and Multiplex Symbolic Execution Research Papers Yinxi Liu Rochester Institute of Technology, Wei Meng Chinese University of Hong Kong, Yinqian Zhang Southern University of Science and Technology DOI | ||
12:00 20mTalk | Smart Contract Fuzzing Towards Profitable Vulnerabilities Research Papers Ziqiao Kong Nanyang Technological University, Cen Zhang Nanyang Technological University, Maoyi Xie Nanyang Technological University, Ming Hu Singapore Management University, Yue Xue MetaTrust Labs, Ye Liu Singapore Management University, Haijun Wang Xi'an Jiaotong University, Yang Liu Nanyang Technological University DOI Pre-print File Attached | ||
Vega is close to the registration desk.
Facing the registration desk, its entrance is on the left, close to the hotel side entrance.