Fault injection attacks represent a class of threats that can compromise embedded systems across multiple layers of abstraction, such as system software, instruction set architecture (ISA), microarchitecture, and physical implementation. Early detection of these vulnerabilities and understanding their root causes along with their propagation from the physical layer to the system software is critical to secure the cyberinfrastructure. This present presents a comprehensive methodology for conducting controlled fault injection attacks at the pre-silicon level and an analysis of the underlying system for root-causing behavior. As the driving application, we use the clock glitch attacks in AI/ML applications for critical misclassification. Our study aims to characterize and diagnose the impact of faults within the RISC-V instruction set and pipeline stages, while tracing fault propagation from the circuit level to the AI/ML application software. This analysis resulted in discovering a novel vulnerability through controlled clock glitch parameters, specifically targeting the RISC-V decode stage.

翻译：故障注入攻击是一类能够跨越多个抽象层级（如系统软件、指令集架构、微架构及物理实现）危害嵌入式系统的威胁。早期检测此类漏洞并理解其根本成因及其从物理层向系统软件的传播路径，对于保障网络基础设施安全至关重要。本文提出一种在流片前阶段实施受控故障注入攻击的系统性方法，并对底层系统进行根源行为分析。作为驱动应用案例，我们以AI/ML应用中的时钟毛刺攻击为研究对象，探究其引发关键误分类的机制。本研究旨在表征和诊断故障在RISC-V指令集及流水线阶段中的影响，同时追踪故障从电路层级到AI/ML应用软件的传播路径。通过控制时钟毛刺参数，该分析发现了一种针对RISC-V译码阶段的新型漏洞。