# HarDNN: Feature Map Vulnerability Evaluation in CNNs

arXiv: https://arxiv.org/abs/2002.09786 · HTML: https://mlsanity.com/paper/2002.09786/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2020.

## Built on by (most cited first, 16 of 16)

- [A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks](https://mlsanity.com/paper/2305.05750/) (2023)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions](https://mlsanity.com/paper/2112.13544/) (2021)
- [Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs](https://mlsanity.com/paper/2104.09455/) (2021)
- [Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision](https://mlsanity.com/paper/2108.07019/) (2021)
- [DeepVigor: Vulnerability Value Ranges and Factors for DNNs' Reliability Assessment](https://mlsanity.com/paper/2303.06931/) (2023)
- [Enhancing Fault Resilience of QNNs by Selective Neuron Splitting](https://mlsanity.com/paper/2306.09973/) (2023)
- [MRFI: An Open Source Multi-Resolution Fault Injection Framework for Neural Network Processing](https://mlsanity.com/paper/2306.11758/) (2023)
- [Cost-Effective Fault Tolerance for CNNs Using Parameter Vulnerability Based Hardening and Pruning](https://mlsanity.com/paper/2405.10658/) (2024)
- [Hybrid Convolutional Neural Networks with Reliability Guarantee](https://mlsanity.com/paper/2405.05146/) (2024)
- [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)
- [Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models](https://mlsanity.com/paper/2406.03229/) (2024)
- [DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural Network](https://mlsanity.com/paper/2410.15742/) (2024)
- [Cross-Layer Optimization for Fault-Tolerant Deep Learning](https://mlsanity.com/paper/2312.13754/) (2023)
- [Threat Modeling for AI: The Case for an Asset-Centric Approach](https://mlsanity.com/paper/2505.06315/) (2025)

## Abstract (arXiv)

As Convolutional Neural Networks (CNNs) are increasingly being employed in safety-critical applications, it is important that they behave reliably in the face of hardware errors. Transient hardware errors may percolate undesirable state during execution, resulting in software-manifested errors which can adversely affect high-level decision making. This paper presents HarDNN, a software-directed approach to identify vulnerable computations during a CNN inference and selectively protect them based on their propensity towards corrupting the inference output in the presence of a hardware error. We show that HarDNN can accurately estimate relative vulnerability of a feature map (fmap) in CNNs using a statistical error injection campaign, and explore heuristics for fast vulnerability assessment. Based on these results, we analyze the tradeoff between error coverage and computational overhead that the system designers can use to employ selective protection. Results show that the improvement in resilience for the added computation is superlinear with HarDNN. For example, HarDNN improves SqueezeNet's resilience by 10x with just 30% additional computations.