TreeFI：面向深度神经网络的值感知统计故障注入
TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks
- Univ Rennes, Inria, IRISA, CNRS（雷恩大学，法国国家信息与自动化研究所，IRISA，法国国家科学研究中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
TreeFI是一种值感知统计故障注入方法，通过回归树划分DNN层的值分布区间并分层分配注入任务，可在保证估计精度的同时大幅减少注入预算，在CNN、Transformer等模型上效果显著。
AI中文摘要：
深度神经网络在硬件故障下的可靠性评估通常依赖故障注入，但对于现代模型和数据集而言， exhaustive（穷尽式）注入是难以处理的。统计故障注入降低了这一成本，但现有方法仍需要大量注入预算，因为它们未明确利用浮点故障的关键特性：位翻转的影响强烈依赖于被损坏的值。我们提出TreeFI，一种面向深度神经网络（DNN）激活值和权重中FP32单比特故障的值感知统计故障注入方法。TreeFI通过回归树学习，将每一层的值分布划分为具有相似位翻转预期行为的区间，并根据各区间对故障率估计的相关性在这些区间间分配注入任务。这种分层分配在保留目标置信度和误差边际的同时，避免了在故障空间的低影响区域进行不必要的注入。我们在CNN和Transformer模型上使用CIFAR-10和ImageNet验证了TreeFI。在ResNet8（其激活故障的穷尽式注入是可行的）上，在相同实验设置下，TreeFI比最先进的统计故障注入（FI）基线提供了更准确的估计。在评估的所有模型中，TreeFI将所需的注入预算减少了多达72.1倍，激活故障的平均减少量为44.9倍，执行的权重注入任务的平均减少量为11.2倍。
英文摘要：
Reliability evaluation of deep neural networks under hardware faults commonly relies on fault injection, but exhaustive campaigns are intractable for modern models and datasets. Statistical fault injection reduces this cost, yet existing approaches still require large injection budgets because they do not explicitly exploit a key property of floating-point faults: the effect of a bit flip depends strongly on the value being corrupted. We propose TreeFI, a value-aware statistical fault-injection methodology for FP32 single-bit faults in DNN activations and weights. TreeFI partitions each layer's value distribution into intervals with similar expected bit-flip behavior, learned using regression trees, and allocates injections across these intervals according to their relevance for failure-rate estimation. This stratified allocation preserves the target confidence and error margin while avoiding unnecessary injections in low-impact regions of the fault space. We validate TreeFI on CNN and Transformer models using CIFAR-10 and ImageNet. On ResNet8, where exhaustive activation fault injection is feasible, TreeFI provides more accurate estimates than state-of-the-art statistical FI baselines under the same campaign setting. Across the evaluated models, TreeFI reduces the required injection budget by up to 72.1x, with average reductions of 44.9x for activation faults and 11.2x for the executed weight campaigns.
