zkCraft: 基于提示的LLM作为零知识电路模糊测试的零样本突变模式Oracle
zkCraft: Prompt-Guided LLM as a Zero-Shot Mutation Pattern Oracle for TCCT-Powered ZK Fuzzing
AI总结：
zkCraft结合确定性R1CS感知本地化与证明承载搜索，通过编码候选约束编辑为Row-Vortex多项式，利用LLM驱动的突变模板检测语义不一致，降低误报并提升ZK电路开发的鲁棒性。
摘要：
零知识电路使隐私保护和可扩展系统成为可能，但因其见证计算与电路约束之间的紧密耦合而难以正确实现。我们提出了zkCraft，一个实用框架，结合确定性、R1CS感知的本地化与证明承载搜索，以检测语义不一致。zkCraft将候选约束编辑编码为单个Row-Vortex多项式，并用Violation IOP替代重复求解器查询，该IOP证明了编辑的存在及其简洁证明。确定性LLM驱动的突变模板将探索偏向边缘情况，同时保持可审计的代数验证。在真实Circom代码上的评估显示，证明承载本地化能检测多样化的欠约束和过约束故障，具有低误报率并减少昂贵的求解器交互。我们的方法连接了形式验证与自动化调试，为稳健的ZK电路开发提供可扩展路径。
英文摘要：
Zero-knowledge circuits enable privacy-preserving and scalable systems but are difficult to implement correctly due to the tight coupling between witness computation and circuit constraints. We present zkCraft, a practical framework that combines deterministic, R1CS-aware localization with proof-bearing search to detect semantic inconsistencies. zkCraft encodes candidate constraint edits into a single Row-Vortex polynomial and replaces repeated solver queries with a Violation IOP that certifies the existence of edits together with a succinct proof. Deterministic LLM-driven mutation templates bias exploration toward edge cases while preserving auditable algebraic verification. Evaluation on real Circom code shows that proof-bearing localization detects diverse under- and over-constrained faults with low false positives and reduces costly solver interaction. Our approach bridges formal verification and automated debugging, offering a scalable path for robust ZK circuit development.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
