From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Xing, Wu, Hao, Liang, Hanzhong, Jiang, Yunlin, Cheng, Yuxi, Liu, Yating, Xu, Fengyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918301984096256
author Su, Xing
Wu, Hao
Liang, Hanzhong
Jiang, Yunlin
Cheng, Yuxi
Liu, Yating
Xu, Fengyuan
author_facet Su, Xing
Wu, Hao
Liang, Hanzhong
Jiang, Yunlin
Cheng, Yuxi
Liu, Yating
Xu, Fengyuan
contents Blockchain systems are increasingly targeted by on-chain attacks that exploit contract vulnerabilities to extract value rapidly and stealthily, making systematic analysis and reproduction highly challenging. In practice, reproducing such attacks requires manually crafting proofs-of-concept (PoCs), a labor-intensive process that demands substantial expertise and scales poorly. In this work, we present the first automated framework for synthesizing verifiable PoCs directly from on-chain attack executions. Our key insight is that attacker logic can be recovered from low-level transaction traces via trace-driven reverse engineering, and then translated into executable exploits by leveraging the code-generation capabilities of large language models (LLMs). To this end, we propose TracExp, which localizes attack-relevant execution contexts from noisy, multi-contract traces and introduces a novel dual-decompiler to transform concrete executions into semantically enriched exploit pseudocode. Guided by this representation, TracExp synthesizes PoCs and refines them to preserve exploitability-relevant semantics. We evaluate TracExp on 321 real-world attacks over the past 20 months. TracExp successfully synthesizes PoCs for 93% of incidents, with 58.78% being directly verifiable, at an average cost of only \$0.07 per case. Moreover, TracExp enabled the release of a large number of previously unavailable PoCs to the community, earning a $900 bounty and demonstrating strong practical impact.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16681
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks
Su, Xing
Wu, Hao
Liang, Hanzhong
Jiang, Yunlin
Cheng, Yuxi
Liu, Yating
Xu, Fengyuan
Cryptography and Security
Software Engineering
Blockchain systems are increasingly targeted by on-chain attacks that exploit contract vulnerabilities to extract value rapidly and stealthily, making systematic analysis and reproduction highly challenging. In practice, reproducing such attacks requires manually crafting proofs-of-concept (PoCs), a labor-intensive process that demands substantial expertise and scales poorly. In this work, we present the first automated framework for synthesizing verifiable PoCs directly from on-chain attack executions. Our key insight is that attacker logic can be recovered from low-level transaction traces via trace-driven reverse engineering, and then translated into executable exploits by leveraging the code-generation capabilities of large language models (LLMs). To this end, we propose TracExp, which localizes attack-relevant execution contexts from noisy, multi-contract traces and introduces a novel dual-decompiler to transform concrete executions into semantically enriched exploit pseudocode. Guided by this representation, TracExp synthesizes PoCs and refines them to preserve exploitability-relevant semantics. We evaluate TracExp on 321 real-world attacks over the past 20 months. TracExp successfully synthesizes PoCs for 93% of incidents, with 58.78% being directly verifiable, at an average cost of only \$0.07 per case. Moreover, TracExp enabled the release of a large number of previously unavailable PoCs to the community, earning a $900 bounty and demonstrating strong practical impact.
title From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks
topic Cryptography and Security
Software Engineering
url https://arxiv.org/abs/2601.16681