用大模型自动完成模糊测试全流程，大幅降低人工成本。
Orion: Fuzzing Workflow Automation
- 结合大模型推理与传统工具，自动分析代码、配置测试环境
- 在多个阶段减少46至204倍的人工工作量，发现clib库两个未知漏洞
- 适合安全研究人员和自动化测试团队快速部署完整模糊测试
模糊测试是发现软件漏洞最有效的技术之一。尽管现代模糊测试工具能自动生成输入并监控执行，但整个流程——从代码分析、钩子配置到结果分类——仍需大量手动操作。以往研究仅关注单一环节，如钩子生成或输入精简，导致研究者需手动拼接各阶段。我们提出Orion框架，通过将大模型推理与传统工具结合，自动处理模糊测试中的关键瓶颈，使测试规模达到人力难以企及的程度。Orion利用大模型进行代码理解与语义引导，同时依赖确定性工具完成验证、迭代优化等高精度任务。在基准测试中，Orion在不同阶段减少46至204倍的人工投入，并成功发现广泛使用的开源库clib中两个此前未知的漏洞。
原文摘要 · Abstract (English)
Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manual effort. Prior attempts focused on single stages such as harness synthesis or input minimization, leaving researchers to manually connect the pieces into a complete fuzzing campaign. We introduce Orion, a framework that automates the the manual bottlenecks of fuzzing by integrating LLM reasoning with traditional tools, allowing campaigns to scale to settings where human effort alone was impractical. Orion uses LLMs for code reasoning and semantic guidance, while relying on deterministic tools for verification, iterative refinement, and tasks that require precision. Across our benchmark suite, Orion reduces human effort by 46-204x depending on the workflow stage, and we demonstrate its effectiveness through the discovery of two previously unknown vulnerabilities in the widely used open-source clib library.
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。