# TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

arXiv: https://arxiv.org/abs/2004.01743 · HTML: https://mlsanity.com/paper/2004.01743/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 22 of 22)

- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks](https://mlsanity.com/paper/2305.05750/) (2023)
- [A Survey on Failure Analysis and Fault Injection in AI Systems](https://mlsanity.com/paper/2407.00125/) (2024)
- [Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs](https://mlsanity.com/paper/2104.09455/) (2021)
- [Fast and Accurate Error Simulation for CNNs against Soft Errors](https://mlsanity.com/paper/2206.02051/) (2022)
- [Winograd Convolution: A Perspective from Fault Tolerance](https://mlsanity.com/paper/2202.08675/) (2022)
- [An Overview of Laser Injection against Embedded Neural Network Models](https://mlsanity.com/paper/2105.01403/) (2021)
- [MRFI: An Open Source Multi-Resolution Fault Injection Framework for Neural Network Processing](https://mlsanity.com/paper/2306.11758/) (2023)
- [Machine Learning in Space: Surveying the Robustness of on-board ML models to Radiation](https://mlsanity.com/paper/2405.02642/) (2024)
- [Statistical Modeling of Soft Error Influence on Neural Networks](https://mlsanity.com/paper/2210.05876/) (2022)
- [Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators](https://mlsanity.com/paper/2212.02649/) (2022)
- [PyGFI: Analyzing and Enhancing Robustness of Graph Neural Networks Against Hardware Errors](https://mlsanity.com/paper/2212.03475/) (2022)
- [Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance](https://mlsanity.com/paper/2308.08230/) (2023)
- [Hardware Resilience Properties of Text-Guided Image Classifiers](https://mlsanity.com/paper/2311.14062/) (2023)
- [DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural Network](https://mlsanity.com/paper/2410.15742/) (2024)
- [PyResBugs: A Dataset of Residual Python Bugs for Natural Language-Driven Fault Injection](https://mlsanity.com/paper/2505.05777/) (2025)
- [A New Perspective On AI Safety Through Control Theory Methodologies](https://mlsanity.com/paper/2506.23703/) (2025)
- [Characterizing Soft-Error Resiliency in Arm's Ethos-U55 Embedded Machine Learning Accelerator](https://mlsanity.com/paper/2404.09317/) (2024)
- [Fault injection analysis of Real NVP normalising flow model for satellite anomaly detection](https://mlsanity.com/paper/2504.02015/) (2025)
- [GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research](https://mlsanity.com/paper/2509.10790/) (2025)
- [TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks](https://mlsanity.com/paper/2609.04912/) (2026)
- [An Empirical Fault Vulnerability Exploration of ReRAM-based Process-in-Memory CNN Accelerators](https://mlsanity.com/paper/2610.07029/) (2026)

## Abstract (arXiv)

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 techniques (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, a high-level fault injection (FI) framework for TensorFlow-based applications. TensorFI is able to inject both hardware and software faults in general TensorFlow programs. TensorFI is a configurable FI tool that is flexible, easy to use, and portable. It can be integrated into existing TensorFlow programs to assess their resilience for different fault types (e.g., faults in particular operators). We use TensorFI to evaluate the resilience of 12 ML programs, including DNNs used in the autonomous vehicle domain. Our tool is publicly available at https://github.com/DependableSystemsLab/TensorFI.