arXiv cs.AI· Zifan Peng, Peng Huang, Jingyi Zheng, Yingjie Xue, Xuechao Wang, Xinlei He, Xia Hu, Dongrui Liu·· 12 小时前AI 评分31
CONSTRAINTDIAL：通过协议变异实现智能合约安全任务的终身构建
Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation
AI 导读
CONSTRAINTDIAL 框架通过协议变异自动化构建智能合约安全任务，从 203 个公开案例生成 3045 个覆盖检测、利用与修补的任务输入。相比仅做合约重建，协议变异使借助公开答案解题的成功率平均下降 10.9 个百分点，靠复制线上答案完成的任务比例下降 9.3 点。该框架自动完成本地合约重建，并以攻击执行结果筛选对调用或输入的改动，使原始攻击失效同时保留可利用性、安全目标与正常功能。
正文 · 原文
Abstract:AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in losses across the broader blockchain ecosystem. Existing evaluations can reward memorized or copied answers, including attack code recovered from public blockchain transactions. Reconstructing contracts and validating tasks also require costly manual effort. To address these issues, we propose CONSTRAINTDIAL, a framework for lifelong construction of smart contract security tasks via protocol mutation. It automates local contract reconstruction and uses attack execution to select changes to the required calls or inputs. Execution checks guide revisions that make the original attack fail while preserving exploitability, the security objective, and normal functionality. New incidents and audit findings enter the same procedure. With CONSTRAINTDIAL, we construct 3,045 task inputs from 203 public cases, covering detect, exploit, and patch. Compared with reconstruction alone, protocol mutation reduces success with supplied public answers by 10.9 percentage points on average across detect, exploit, and patch. The fraction of tasks solved by copying online answers falls by 9.3 points.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32453 [cs.CR] |
| (or arXiv:2610.32453v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32453 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zifan Peng [view email]
[v1]
Fri, 23 Oct 2026 10:17:43 UTC (439 KB)
来源：arXiv cs.AI · arxiv.org