English(EN) TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks

TreeFI方法将DNN故障注入成本降低高达72倍

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员开发了TreeFI，一种新颖的面向价值的统计故障注入方法，旨在提高深度神经网络的可靠性评估。该方法专门针对FP32激活和权值中的单比特故障，使用回归树将值分布划分为具有相似故障行为的区间。通过根据故障率估计的相关性分配注入，TreeFI显著减少了所需的注入预算，与现有方法相比，降低了高达72.1倍。该方法已在CNN和Transformer模型上使用CIFAR-10和ImageNet数据集进行了验证，证明了在更少注入的情况下比最先进的基线方法更准确的估计。 AI

影响降低了评估DNN可靠性的计算成本，有可能加速更强大的AI系统的部署。

排序理由学术论文，详细介绍了DNN可靠性评估的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了DNN可靠性评估的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Noam Bires, Marcello Traiola, Angeliki Kritikakou, Elisa Fromont · 2026-09-07 04:00

TreeFI：深度神经网络的面向价值的统计故障注入

arXiv:2609.04912v1 Announce Type: cross Abstract: 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 e…

本文如何被排名

报道来源 [1]

TreeFI：深度神经网络的面向价值的统计故障注入

相关实体

相关话题