.png){kind=icon}
返回
Fault Injection for TensorFlow Applications
.png){kind=icon}
OA
AI
DOI：10.1109/TDSC.2022.3175930.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As machine learning (ML) has seen increasing adoption in safety-critical domains (e.g., autonomous vehicles), the reliability of ML systems has also grown in importance. While prior studies have proposed techniques to enable efficient error-resilience (e.g., selective instruction duplication), a fundamental requirement for realizing these techniques is a detailed understanding of the application's resilience. In this work, we present TensorFI 1 and TensorFI 2, high-level fault injection (FI) frameworks for TensorFlow-based applications. TensorFI 1 and 2 are able to inject both hardware and software faults in any general TensorFlow 1 and 2 program respectively. Both are configurable FI tools that are flexible, easy to use, and portable. They can be integrated into existing TensorFlow programs to assess their resilience for different fault types (e.g., bit-flips in particular operations or layers). We use TensorFI 1 and TensorFI 2 to evaluate the resilience of 11 and 10 ML programs respectively, all written in TensorFlow, including DNNs used in the autonomous vehicle domain. The results give us insights into why some of the models are more resilient. We also measure the performance overheads of the two injectors, and present 4 case studies, two for each tool, to demonstrate their utility.
Keyword:
Deep neural networks
error resilience
fault injection
machine learning
TensorFlow
期刊
IF:
7.5
论文数:
2.5K
被引数:
9.6K
机构
引用论文
分享收藏分享收藏分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Role of simple descriptors and applicability domain in predicting change in protein thermostability.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏分享收藏分享收藏
查看更多内容