EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive Mutation Scheduling with Deep Reinforcement Learning for Smart Contract Fuzzing

Qianqian Pang, Xin Yin, Tingting Bi, Lingfeng Bao, Chao Ni, Xiaohu Yang

Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 2560-2582

DOI: 10.1145/3808121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Qianqian Pang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart contracts underpin a wide range of decentralized applications—from financial services to supply-chain management—but their immutability and direct control of assets magnify the impact of any security bugs. Although many fuzz approaches have been proposed and have demonstrated their effectiveness in uncovering vulnerabilities, existing methods often rely on unguided random mutation scheduling, generate redundant inputs, and fail to adapt to smart contract-specific characteristics. To overcome these challenges, we present FuzzMaster, a feedback-driven fuzzing framework that combines deep reinforcement learning (DRL) with lightweight probabilistic scheduling to steer mutation selection at runtime intelligently. By continuously analyzing execution feedback—code coverage, function-call sequences, and vulnerability signals—FuzzMaster’s DRL agent and probabilistic tables prioritize high-impact mutations and avoid wasted effort on redundant seeds. On standard VeriSmart and SmartBugs benchmarks, FuzzMaster achieves a 66.2% detection rate with 100% precision (versus 46.9% for ItyFuzz and 43.1% for Confuzzius) and uncovers most bugs within the first second of execution. Meanwhile, in real-world Ethereum contracts, FuzzMaster identified 97 vulnerabilities in 6 categories. These results demonstrate that dynamic, vulnerability-aware mutation scheduling can dramatically improve both the efficiency and effectiveness of smart contract fuzz testing.

Zitieren

APA

Pang, Q., Yin, X., Bi, T., Bao, L., Ni, C., & Yang, X. (2026). Adaptive Mutation Scheduling with Deep Reinforcement Learning for Smart Contract Fuzzing. Proceedings of the ACM on Software Engineering, 3(FSE), 2560-2582. https://doi.org/10.1145/3808121

Vancouver

Pang Q, Yin X, Bi T, Bao L, Ni C, Yang X. Adaptive Mutation Scheduling with Deep Reinforcement Learning for Smart Contract Fuzzing. Proceedings of the ACM on Software Engineering. 2026;3(FSE):2560-2582. doi:10.1145/3808121

BibTeX
@article{Pang2026,
  author = {Pang, Qianqian and Yin, Xin and Bi, Tingting and Bao, Lingfeng and Ni, Chao and Yang, Xiaohu},
  title = {Adaptive Mutation Scheduling with Deep Reinforcement Learning for Smart Contract Fuzzing},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2026},
  volume = {3},
  number = {FSE},
  pages = {2560--2582},
  doi = {10.1145/3808121}
}
Kostenlos starten →