TxRay: Agentic Postmortem of Live Blockchain Attacks

2026-02-01

AI Summary

This work addresses the inefficiency and incompleteness of manual postmortem analyses in DeFi attacks, which often suffer from limited on-chain evidence and risk missing critical details. To overcome this, we propose the first automated system that integrates large language model (LLM) agents with executable semantic assertions to reconstruct the full lifecycle of Anyone-Can-Take–style attacks from minimal transaction seeds. The system generates self-verifiable, hardcoding-free proof-of-concept (PoC) exploits and introduces PoCEvaluator, an independent evaluation framework to ensure output quality. Evaluated on 114 real-world incidents, our approach achieves a 92.11% end-to-end reproduction rate, with 98.1% of generated PoCs generalizing to new contract addresses. It localizes root causes in a median of 40 minutes and produces functional PoCs within 59 minutes.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Multiagent Systems: Adversarial Agents
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but this openness exposes pools of value controlled by code. Within five years, the DeFi ecosystem has lost over 15.75B USD to reported exploits. Many exploits arise from permissionless opportunities that any participant can trigger using only public state and standard interfaces, which we call Anyone-Can-Take (ACT) opportunities. Despite on-chain transparency, postmortem analysis remains slow and manual: investigations start from limited evidence, sometimes only a single transaction hash, and must reconstruct the exploit lifecycle by recovering related transactions, contract code, and state dependencies. We present TxRay, a Large Language Model (LLM) agentic postmortem system that uses tool calls to reconstruct live ACT attacks from limited evidence. Starting from one or more seed transactions, TxRay recovers the exploit lifecycle, derives an evidence-backed root cause, and generates a runnable, self-contained Proof of Concept (PoC) that deterministically reproduces the incident. TxRay self-checks postmortems by encoding incident-specific semantic oracles as executable assertions. To evaluate PoC correctness and quality, we develop PoCEvaluator, an independent agentic execution-and-review evaluator. On 114 incidents from DeFiHackLabs, TxRay produces an expert-aligned root cause and an executable PoC for 105 incidents, achieving 92.11% end-to-end reproduction. Under PoCEvaluator, 98.1% of TxRay PoCs avoid hard-coding attacker addresses, a +22.9pp lift over DeFiHackLabs. In a live deployment, TxRay delivers validated root causes in 40 minutes and PoCs in 59 minutes at median latency. TxRay's oracle-validated PoCs enable attack imitation, improving coverage by 15.6% and 65.5% over STING and APE.

Problem

• DeFi
• postmortem analysis
• blockchain attacks
• ACT opportunities
• exploit reconstruction

Innovation

• Agentic Postmortem
• Anyone-Can-Take (ACT) Exploits
• LLM Tool Use
• Executable Proof of Concept
• Semantic Oracles