SENTAUR：利用大语言模型针对不良修订的安全增强型硬件木马评估
SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions
AI总结：
针对集成电路供应链中的硬件木马风险，提出基于大语言模型的SENTAUR框架，无需学习周期即可生成并净化RTL级HT实例，实现快速评估，且可推广至自动功能修改。
摘要：
全球分布的集成电路供应链因不可信的第三方而带来风险。这些风险涵盖无意使用硬件木马（HT）、插入的知识产权（3P-IP）或电子设计自动化（EDA）流程。硬件木马可能引入隐蔽的HT行为，阻止集成电路按预期工作，或通过侧信道泄露敏感数据。为了对抗硬件木马，快速审查HT场景是一项关键需求。虽然Trust-Hub基准是评估防御措施的良好起点，但它们在HT设计的广阔范围内仅包含一小部分手动创建的HT。此外，HT可能在综合过程中消失。我们提出了一个大语言模型（LLM）框架SENTAUR，通过学习寄存器传输级（RTL）设计的规格、描述和HT效果的自然语言描述，为其生成一套合法的HT。现有工具和基准存在局限性；它们需要学习周期来构建模拟威胁模型的机器学习模型，且难以复现。SENTAUR可以利用LLM快速生成HT实例，无需学习周期，并净化HT以促进其快速评估。对SENTAUR的评估涉及从TrustHub和其他来源生成有效、可综合且实用的HT，研究RTL上负载/触发器的影响。虽然我们的评估侧重于HT插入，但SENTAUR可以推广到自动将RTL代码转换为具有定义的功能修改。
英文摘要：
A globally distributed IC supply chain brings risks due to untrusted third parties. The risks span inadvertent use of hardware Trojan (HT), inserted Intellectual Property (3P-IP) or Electronic Design Automation (EDA) flows. HT can introduce stealthy HT behavior, prevent an IC work as intended, or leak sensitive data via side channels. To counter HTs, rapidly examining HT scenarios is a key requirement. While Trust-Hub benchmarks are a good starting point to assess defenses, they encompass a small subset of manually created HTs within the expanse of HT designs. Further, the HTs may disappear during synthesis. We propose a large language model (LLM) framework SENTAUR to generate a suite of legitimate HTs for a Register Transfer Level (RTL) design by learning its specifications, descriptions, and natural language descriptions of HT effects. Existing tools and benchmarks are limited; they need a learning period to construct an ML model to mimic the threat model and are difficult to reproduce. SENTAUR can swiftly produce HT instances by leveraging LLMs without any learning period and sanitizing the HTs facilitating their rapid assessment. Evaluation of SENTAUR involved generating effective, synthesizable, and practical HTs from TrustHub and elsewhere, investigating impacts of payloads/triggers at the RTL. While our evaluation focused on HT insertion, SENTAUR can generalize to automatically transform an RTL code to have defined functional modifications.
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。
