# DeepVigor: Vulnerability Value Ranges and Factors for DNNs' Reliability Assessment

arXiv: https://arxiv.org/abs/2303.06931 · HTML: https://mlsanity.com/paper/2303.06931/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 4 of 4)

- [Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead](https://mlsanity.com/paper/2101.02559/) (2021)
- [FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation](https://mlsanity.com/paper/1912.00941/) (2019)
- [HarDNN: Feature Map Vulnerability Evaluation in CNNs](https://mlsanity.com/paper/2002.09786/) (2020)
- [FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions](https://mlsanity.com/paper/2112.13544/) (2021)

## Built on by (most cited first, 7 of 7)

- [DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Accelerators](https://mlsanity.com/paper/2303.08226/) (2023)
- [Enhancing Fault Resilience of QNNs by Selective Neuron Splitting](https://mlsanity.com/paper/2306.09973/) (2023)
- [Special Session: Approximation and Fault Resiliency of DNN Accelerators](https://mlsanity.com/paper/2306.04645/) (2023)
- [Cost-Effective Fault Tolerance for CNNs Using Parameter Vulnerability Based Hardening and Pruning](https://mlsanity.com/paper/2405.10658/) (2024)
- [ProAct: Progressive Training for Hybrid Clipped Activation Function to Enhance Resilience of DNNs](https://mlsanity.com/paper/2406.06313/) (2024)
- [DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural Network](https://mlsanity.com/paper/2410.15742/) (2024)
- [PhD Thesis Summary: Methods for Reliability Assessment and Enhancement of Deep Neural Network Hardware Accelerators](https://mlsanity.com/paper/2603.08724/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) and their accelerators are being deployed ever more frequently in safety-critical applications leading to increasing reliability concerns. A traditional and accurate method for assessing DNNs' reliability has been resorting to fault injection, which, however, suffers from prohibitive time complexity. While analytical and hybrid fault injection-/analytical-based methods have been proposed, they are either inaccurate or specific to particular accelerator architectures. In this work, we propose a novel accurate, fine-grain, metric-oriented, and accelerator-agnostic method called DeepVigor that provides vulnerability value ranges for DNN neurons' outputs. An outcome of DeepVigor is an analytical model representing vulnerable and non-vulnerable ranges for each neuron that can be exploited to develop different techniques for improving DNNs' reliability. Moreover, DeepVigor provides reliability assessment metrics based on vulnerability factors for bits, neurons, and layers using the vulnerability ranges. The proposed method is not only faster than fault injection but also provides extensive and accurate information about the reliability of DNNs, independent from the accelerator. The experimental evaluations in the paper indicate that the proposed vulnerability ranges are 99.9% to 100% accurate even when evaluated on previously unseen test data. Also, it is shown that the obtained vulnerability factors represent the criticality of bits, neurons, and layers proficiently. DeepVigor is implemented in the PyTorch framework and validated on complex DNN benchmarks.