# Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision

arXiv: https://arxiv.org/abs/2108.07019 · HTML: https://mlsanity.com/paper/2108.07019/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks](https://mlsanity.com/paper/1906.01017/) (2019)
- [FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation](https://mlsanity.com/paper/1912.00941/) (2019)
- [Silent Data Corruptions at Scale](https://mlsanity.com/paper/2102.11245/) (2021)
- [FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks](https://mlsanity.com/paper/2003.12203/) (2020)
- [HarDNN: Feature Map Vulnerability Evaluation in CNNs](https://mlsanity.com/paper/2002.09786/) (2020)
- [A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction](https://mlsanity.com/paper/2003.13874/) (2020)
- [MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNs](https://mlsanity.com/paper/2010.14687/) (2020)

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

- [Hardware faults that matter: Understanding and Estimating the safety impact of hardware faults on object detection DNNs](https://mlsanity.com/paper/2209.03225/) (2022)
- [A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks](https://mlsanity.com/paper/2310.20349/) (2023)
- [Hybrid Convolutional Neural Networks with Reliability Guarantee](https://mlsanity.com/paper/2405.05146/) (2024)
- [Large-Scale Application of Fault Injection into PyTorch Models -- an Extension to PyTorchFI for Validation Efficiency](https://mlsanity.com/paper/2310.19449/) (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)
- [TERMon: Detecting Persistent Behavioral Threats in Edge AI via Hardware-Native Ternary Runtime Monitor](https://mlsanity.com/paper/2609.21713/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have become an established part of numerous safety-critical computer vision applications, including human robot interactions and automated driving. Real-world implementations will need to guarantee their robustness against hardware soft errors corrupting the underlying platform memory. Based on the previously observed efficacy of activation clipping techniques, we build a prototypical safety case for classifier CNNs by demonstrating that range supervision represents a highly reliable fault detector and mitigator with respect to relevant bit flips, adopting an eight-exponent floating point data representation. We further explore novel, non-uniform range restriction methods that effectively suppress the probability of silent data corruptions and uncorrectable errors. As a safety-relevant end-to-end use case, we showcase the benefit of our approach in a vehicle classification scenario, using ResNet-50 and the traffic camera data set MIOVision. The quantitative evidence provided in this work can be leveraged to inspire further and possibly more complex CNN safety arguments.