用分层强化学习生成更优测试用例，提升CPU验证效率。
HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing
- 分两层生成：程序层规划结构，指令层精准填充。
- 在三个RISC-V核心上覆盖率达90%以上，检出更多漏洞。
- 自适应奖励机制+语义编码器，适合硬件验证工程师使用。
现代处理器验证因传统变异式模糊测试效率低下，难以触及深层架构状态。本文提出HiFuzz，一种新型分层强化学习框架，将变异替换为两级结构化生成过程：程序代理负责全局布局，基本块代理负责精确指令填充。为缓解奖励稀疏问题，引入自适应覆盖率奖励机制和语义感知的基本块编码器，提供内在反馈。在三个真实RISC-V核心上的大量评估表明，HiFuzz在覆盖率和漏洞检测方面显著优于现有顶尖模糊测试工具。
原文摘要 · Abstract (English)
Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that replaces mutation with a structured, two-layer generation process: a Program Agent for global layout and a Basic Block Agent for precise instruction filling. To overcome reward sparsity, HiFuzz integrates an adaptive coverage reward mechanism and a semantic-aware basic block encoder providing intrinsic feedback. Extensive evaluations on three real-world RISC-V cores demonstrate that HiFuzz significantly outperforms state-of-the-art fuzzers in coverage and bug detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。