Assertain:利用大语言模型实现自动安全断言生成
Assertain: Automated Security Assertion Generation Using Large Language Models
AI总结:
本文提出Assertain框架,通过RTL分析、CWE映射和威胁模型智能,利用大语言模型生成安全属性和可执行SystemVerilog断言,提升硬件安全验证效率与准确性。
摘要:
现代系统级芯片设计复杂性增加,加剧了硬件安全风险,手动安全属性规范成为形式化验证的主要瓶颈。本文提出Assertain,集成了RTL设计分析、常见弱点枚举(CWE)映射和威胁模型智能,自动生成功能安全属性和可执行SystemVerilog断言。Assertain利用大语言模型,结合自反思细化机制,确保语法正确性和语义一致性。在11个代表性硬件设计上评估,Assertain在正确断言生成、唯一CWE覆盖和架构缺陷检测方面分别比GPT-5高出61.22%、59.49%和67.92%。这些结果表明,Assertain显著扩展了漏洞覆盖范围,提高了断言质量,并减少了硬件安全验证的人工工作量。
英文摘要:
The increasing complexity of modern system-on-chip designs amplifies hardware security risks and makes manual security property specification a major bottleneck in formal property verification. This paper presents Assertain, an automated framework that integrates RTL design analysis, Common Weakness Enumeration (CWE) mapping, and threat model intelligence to automatically generate security properties and executable SystemVerilog Assertions. Assertain leverages large language models with a self-reflection refinement mechanism to ensure both syntactic correctness and semantic consistency. Evaluated on 11 representative hardware designs, Assertain outperforms GPT-5 by 61.22%, 59.49%, and 67.92% in correct assertion generation, unique CWE coverage, and architectural flaw detection, respectively. These results demonstrate that Assertain significantly expands vulnerability coverage, improves assertion quality, and reduces manual effort in hardware security verification.
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。