The reliability of Neural Networks has gained significant attention, prompting efforts to develop SW-based hardening techniques for safety-critical scenarios. However, evaluating hardening techniques using application-level fault injection (FI) strategies, which are commonly hardware-agnostic, may yield misleading results. This study for the first time compares two FI approaches (at the application level (APP) and instruction level (ISA)) to evaluate deep neural network SW hardening strategies. Results show that injecting permanent faults at ISA (a more detailed abstraction level than APP) changes completely the ranking of SW hardening techniques, in terms of both reliability and accuracy. These results highlight the relevance of using an adequate analysis abstraction for evaluating such techniques.

翻译：神经网络可靠性已引起广泛关注，促使研究界为安全关键场景开发基于软件的加固技术。然而，使用通常与硬件无关的应用级故障注入策略评估加固技术，可能会产生误导性结果。本研究首次比较了两种故障注入方法（应用级和指令级）来评估深度神经网络软件加固策略。结果表明，在指令级注入永久性故障（比应用级更精细的抽象层次）会完全改变软件加固技术在可靠性和准确性方面的排序。这些发现凸显了使用恰当分析抽象层次评估此类技术的重要性。