一句话：提出两阶段多智能体 LLM 框架 FaultSeeker，实现多合约区块链交易的故障定位，显著超越现有工具与原生 LLM。
Web3 与 DeFi 协议锁仓规模已超千亿美元，攻击事件频发造成巨额损失，但事后故障定位平均需分析师 16.7 小时：区块链执行模型复杂、协议交互快速演化、多合约攻击模式超出既有分析能力。现有区块链专用工具仅覆盖单一漏洞类型，唯一的综合方案 DAppFL 依赖机器学习模型，易漏检复杂攻击且缺乏可解释性；LLM 虽具备代码理解能力，但其应用多集中于事前漏洞检测，事后故障定位探索不足。本文提出 FaultSeeker，采用两阶段架构：先进行交易级取证以战略性界定范围，再由协调的专家智能体进行持续推理；通过 orchestrator 智能体实现长期记忆管理，并由协同 worker 分配专门注意力，从而在复杂多合约交易中避免上下文丢失。作者构建了含 115 个真实恶意交易、由专家验证标注的编译数据集，覆盖多种攻击模式与复杂度。实验表明 FaultSeeker 显著优于 DAppFL 及 GPT-4o、Claude 3.7 Sonnet、DeepSeek R1 等原生 LLM，同时保持实用效率（4.4–8.6 分钟）与成本优势（每笔交易 1.55–4.53 美元）。
Web3 applications, particularly decentralized finance (DeFi) protocols, have grown rapidly with over $100 billion locked in smart contracts, attracting sophisticated attacks causing billions in losses. When attack occur, security analysts need to perform fault localization to identify vulnerable functions and understand attack vectors. This critical process currently requires an average of 16.7 analyst hours per incident due to complex blockchain execution models, rapidly evolving protocol interactions, and multi-contract attack patterns that exceed existing analytical capabilities. Despite its critical importance, blockchain fault localization has received limited attention due to fundamental challenges requiring semantic understanding of economic models and protocol-specific logic. Existing blockchain-specific tools target only single vulnerability types, while the only comprehensive solution, DAppFL, relies on machine learning model that may miss sophisticated exploits and lacks interpretability in results. Recent advances in large language models (LLMs) demonstrate remarkable code comprehension capabilities, but existing applications focus on proactive vulnerability detection with minimal exploration of post-incident fault localization.We present FaultSeeker, an LLM-empowered framework for blockchain transaction fault localization. Our two-stage architecture combines transaction-level forensics for strategic scoping with coordinated specialist agents for sustained reasoning. This design provides long-term memory management via orchestrator agents and specialized attention allocation through coordinated workers, enabling comprehensive analysis across complex multi-contract transactions without context loss. We evaluate Fault-Seeker on a compiled dataset of 115 real-world malicious transactions with expert-validated annotations spanning diverse attack patterns and complexity levels. Results demonstrate that FaultSeeker significantly outperforms existing approaches, including DAppFL and leading native LLMs (GPT-4o, Claude 3.7 Sonnet, DeepSeek R1), while maintaining practical efficiency (4.4- 8.6 minutes) and cost-effectiveness ($1.55-$4.53 per transaction).
DOI 原文 ·
@inproceedings{paperbot9313,
title = {Faultseeker: LLM-Empowered Framework for Blockchain Transaction Fault Localization},
author = {Kairan Sun and Zhengzi Xu and Kaixuan Li and Lyuye Zhang and Yuqiang Sun and Liwei Tan and Yang Liu},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00017}
}