Physical Unclonable Functions (PUFs) Entangled Trusted Computing Base
Physical Unclonable Functions (PUFs) Entangled Trusted Computing Base
复制标题
物理不可克隆函数 (PUF) 纠缠可信计算基础
DOI：
10.1109/ises47678.2019.00047
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
A. Tyagi
中科院分区：
文献类型：
--
作者：
Hala Hamadeh;A. Tyagi
这项工作的核心是软件测量物理不可克隆功能（PUF）。它以与所有 PUF 类似的方式测量处理器芯片 ALU 硅生物识别。此外，它以难以通过数学模型分解的方式将硅测量与特定程序指令的数据相关延迟组合在一起。这种方法确保每条软件指令在计算时都得到测量。 SW-PUF 测量将软件的执行绑定到具有相应证书的特定处理器。这使得 SW-PUF 成为需要可信计算的应用程序的有希望的候选者。例如，它可以通过生成特定程序执行路径和处理器芯片独有的签名来测量执行路径的完整性。我们提出了一种基于 SW-PUF 的区域和节能方案，为测量提供比现有可信平台模块 (TPM) 更强大的信任根。为了探索所提出设计的可行性，SW-PUF 已使用 45 nm 技术在 HSPICE 中实现，并在 FPGA 平台上进行评估。
The center-piece of this work is a software measurement physical unclonable function (PUF). It measures processor chip ALU silicon biometrics in a manner similar to all PUFs. Additionally, it composes the silicon measurement with the data-dependent delay of a particular program instruction in a way that is difficult to decompose through a mathematical model. This approach ensures that each software instruction is measured if computed. The SW-PUF measurements bind the execution of software to a specific processor with a corresponding certificate. This makes the SW-PUF a promising candidate for applications requiring Trusted Computing. For instance, it could measure the integrity of an execution path by generating a signature that is unique to the specific program execution path and the processor chip. We present an area and energy-efficient scheme based on the SW-PUF to provide a more robust root of trust for measurement than the existing trusted platform module (TPM). To explore the feasibility of the proposed design, the SW-PUF has been implemented in HSPICE using 45 nm technology and evaluated on the FPGA platform.