# Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects

arXiv: https://arxiv.org/abs/2302.06086 · HTML: https://mlsanity.com/paper/2302.06086/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 72 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Bounding and Counting Linear Regions of Deep Neural Networks](https://mlsanity.com/paper/1711.02114/) (2017)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Convergence Analysis of Two-layer Neural Networks with ReLU Activation](https://mlsanity.com/paper/1705.09886/) (2017)
- [SoK: Certified Robustness for Deep Neural Networks](https://mlsanity.com/paper/2009.04131/) (2020)
- [Taxonomy of Real Faults in Deep Learning Systems](https://mlsanity.com/paper/1910.11015/) (2019)
- [PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations](https://mlsanity.com/paper/2103.03638/) (2021)
- [TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing](https://mlsanity.com/paper/1807.10875/) (2018)
- [Introduction to Neural Network Verification](https://mlsanity.com/paper/2109.10317/) (2021)
- [Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2104.04413/) (2021)
- [DeepLocalize: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/2103.03376/) (2021)
- [RobOT: Robustness-Oriented Testing for Deep Learning Systems](https://mlsanity.com/paper/2102.05913/) (2021)
- [Silent Bugs in Deep Learning Frameworks: An Empirical Study of Keras and TensorFlow](https://mlsanity.com/paper/2112.13314/) (2021)
- [InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees](https://mlsanity.com/paper/2012.07023/) (2020)
- [NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation](https://mlsanity.com/paper/2009.09943/) (2020)
- [Certified Robustness to Programmable Transformations in LSTMs](https://mlsanity.com/paper/2102.07818/) (2021)
- [Self-Checking Deep Neural Networks in Deployment](https://mlsanity.com/paper/2103.02371/) (2021)
- [DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning](https://mlsanity.com/paper/2202.03493/) (2022)
- [LinSyn: Synthesizing Tight Linear Bounds for Arbitrary Neural Network Activation Functions](https://mlsanity.com/paper/2201.13351/) (2022)
- [Operation is the hardest teacher: estimating DNN accuracy looking for mispredictions](https://mlsanity.com/paper/2102.04287/) (2021)

## Built on by (most cited first, 3 of 3)

- [Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks](https://mlsanity.com/paper/2506.14813/) (2025)
- [Terrain Classification Enhanced with Uncertainty for Space Exploration Robots from Proprioceptive Data](https://mlsanity.com/paper/2407.03241/) (2024)
- [BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization](https://mlsanity.com/paper/2602.23630/) (2026)

## Abstract (arXiv)

With the widespread deployment of deep neural networks (DNNs), ensuring the reliability of DNN-based systems is of great importance. Serious reliability issues such as system failures can be caused by numerical defects, one of the most frequent defects in DNNs. To assure high reliability against numerical defects, in this paper, we propose the RANUM approach including novel techniques for three reliability assurance tasks: detection of potential numerical defects, confirmation of potential-defect feasibility, and suggestion of defect fixes. To the best of our knowledge, RANUM is the first approach that confirms potential-defect feasibility with failure-exhibiting tests and suggests fixes automatically. Extensive experiments on the benchmarks of 63 real-world DNN architectures show that RANUM outperforms state-of-the-art approaches across the three reliability assurance tasks. In addition, when the RANUM-generated fixes are compared with developers' fixes on open-source projects, in 37 out of 40 cases, RANUM-generated fixes are equivalent to or even better than human fixes.