ChainDelta: Automatic Patch-Based Exploit Generation for Ethereum with Fuzzing Agents
Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 3392-3414
DOI: 10.1145/3808157 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Mingxi Ye und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, NSFC-RGC Collaborative Research, General Program of the Natural Science Foundation of Guangdong Province, China.
Abstract (Originalsprache)
Given the critical nature of Ethereum, exploiting 1-day vulnerabilities that are patched but not yet widely deployed is essential. Meanwhile, Automatic Patch-based Exploit Generation (APEG) is a promising technique for this, as it helps developers understand root causes, verify fixes in downstream forks, and detect incomplete patches. However, existing exploit generation tools can not work well for vulnerabilities on Ethereum due to three key unique challenges: (1) navigating complex and cross-language exploit paths hidden within patches, (2) synthesizing complicated and stateful environment configurations, and (3) handling non-deterministic inconsistencies between blockchain nodes that lead to false alarms. To address these challenges, we introduce ChainDelta , a novel fuzzing agent framework driven by Large Language Models to automatically generate exploits based on Ethereum security patches. ChainDelta consists of three core modules: a directed fuzzer utilizes call graph analysis to guide testing towards vulnerable code based on the patch information; an agent-based environment fuzzer acts as an expert to automatically set up the necessary blockchain states to trigger vulnerabilities; and finally, a state-aware sanitizer performs differential analysis while monitoring the blockchain transient state to distinguish true inconsistencies from benign non-determinism. We evaluate ChainDelta on a diverse benchmark with real-world patches, covering a wide range of types such as data racing and denial-of-service. ChainDelta successfully generated exploits with a 64% success rate and only a 15.8% false positive rate. An ablation study confirms the contribution of each module to the overall performance. To demonstrate its practical impacts, we conducted a real-world auditing campaign on top of ChainDelta , leading to the discovery of four previously undisclosed vulnerabilities with bug bounties.
Förderung
- National Natural Science Foundation of China
- NSFC-RGC Collaborative Research
- General Program of the Natural Science Foundation of Guangdong Province, China
- Guangdong Zhujiang Talent Program
Zitieren
APA
Ye, M., Nan, Y., Zhong, Z., Su, J., Lin, X., Zheng, P., & Zheng, Z. (2026). ChainDelta: Automatic Patch-Based Exploit Generation for Ethereum with Fuzzing Agents. Proceedings of the ACM on Software Engineering, 3(FSE), 3392-3414. https://doi.org/10.1145/3808157
Vancouver
Ye M, Nan Y, Zhong Z, Su J, Lin X, Zheng P, et al. ChainDelta: Automatic Patch-Based Exploit Generation for Ethereum with Fuzzing Agents. Proceedings of the ACM on Software Engineering. 2026;3(FSE):3392-3414. doi:10.1145/3808157
BibTeX
@article{Ye2026,
author = {Ye, Mingxi and Nan, Yuhong and Zhong, Zhijie and Su, Jianzhong and Lin, Xingwei and Zheng, Peilin and Zheng, Zibin},
title = {ChainDelta: Automatic Patch-Based Exploit Generation for Ethereum with Fuzzing Agents},
journal = {Proceedings of the ACM on Software Engineering},
year = {2026},
volume = {3},
number = {FSE},
pages = {3392--3414},
doi = {10.1145/3808157}
}
EUVIMED