用多智能体LLM系统自动挖掘RTL代码安全漏洞，提升硬件验证效率。
MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models
- 构建多智能体框架，模拟工程师思维逐层排查漏洞。
- 在OpenTitan测试中发现51个问题，其中19个为真实漏洞。
- 融合多种工具与LLM检测，适合硬件安全团队使用。
硬件安全验证是一项复杂且耗时的任务。设计工程师通常依赖形式化验证、静态检查、功能仿真测试，并结合深入的设计分析。大语言模型（LLMs）已被用于辅助该过程，或与现有工具结合使用。本文提出MARVEL，一种基于多智能体的LLM框架，实现决策、工具调用与推理的统一。MARVEL模仿设计师在RTL代码中寻找安全漏洞的认知过程：由监督代理根据安全文档制定SoC安全策略，并分配任务给执行代理；每个执行代理采用特定策略，使用形式工具、静态分析器、lint工具、仿真测试或基于LLM的检测方法识别潜在安全缺陷，将结果反馈给监督代理进行分析确认。我们在基于OpenTitan的已知漏洞SoC上测试该方法，该SoC来自Hack@DATE竞赛。MARVEL共报告51个问题，其中19个为有效安全漏洞，14个为具体警告，18个为幻觉误报。
原文摘要 · Abstract (English)
Hardware security verification is a challenging and time-consuming task. Design engineers may use formal verification, linting, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Language Models (LLMs) have been used to assist during this task, either directly or in conjunction with existing tools. We improve the state of the art by proposing MARVEL, a multi-agent LLM framework for a unified approach to decision-making, tool use, and reasoning. MARVEL mimics the cognitive process of a designer looking for security vulnerabilities in RTL code. It consists of a supervisor agent that devises the security policy of the system-on-chips (SoCs) using its security documentation. It delegates tasks to validate the security policy to individual executor agents. Each executor agent carries out its assigned task using a particular strategy. Each executor agent may use one or more tools to identify potential security bugs in the design and send the results back to the supervisor agent for further analysis and confirmation. MARVEL includes executor agents that leverage formal tools, linters, simulation tests, LLM-based detection schemes, and static analysis-based checks. We test our approach on a known buggy SoC based on OpenTitan from the Hack@DATE competition. We find that of the 51 issues reported by MARVEL, 19 are valid security vulnerabilities, 14 are concrete warnings, and 18 are hallucinated reports.
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。