# A causal model of safety assurance for machine learning

arXiv: https://arxiv.org/abs/2201.05451 · HTML: https://mlsanity.com/paper/2201.05451/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 14 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Analysis of classifiers' robustness to adversarial perturbations](https://mlsanity.com/paper/1502.02590/) (2015)
- [Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges](https://mlsanity.com/paper/1905.04223/) (2019)
- [An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software](https://mlsanity.com/paper/1709.02435/) (2017)
- [Adversarial Examples on Object Recognition: A Comprehensive Survey](https://mlsanity.com/paper/2008.04094/) (2020)
- [Towards Dependability Metrics for Neural Networks](https://mlsanity.com/paper/1806.02338/) (2018)
- [From Black-box to White-box: Examining Confidence Calibration under different Conditions](https://mlsanity.com/paper/2101.02971/) (2021)
- [Safety Metrics for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2105.10142/) (2021)
- [An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks](https://mlsanity.com/paper/1806.01477/) (2018)

## Built on by (most cited first, 2 of 2)

- [A Gradient-based Causal Discovery Framework with Applications to Complex Industrial Processes](https://mlsanity.com/paper/2507.11178/) (2025)
- [Detecting Trojaned DNNs via Spectral Regression Analysis](https://mlsanity.com/paper/2605.21146/) (2026)

## Abstract (arXiv)

This paper proposes a framework based on a causal model of safety upon which effective safety assurance cases for ML-based applications can be built. In doing so, we build upon established principles of safety engineering as well as previous work on structuring assurance arguments for ML. The paper defines four categories of safety case evidence and a structured analysis approach within which these evidences can be effectively combined. Where appropriate, abstract formalisations of these contributions are used to illustrate the causalities they evaluate, their contributions to the safety argument and desirable properties of the evidences. Based on the proposed framework, progress in this area is re-evaluated and a set of future research directions proposed in order for tangible progress in this field to be made.