# Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

arXiv: https://arxiv.org/abs/2102.01564 · HTML: https://mlsanity.com/paper/2102.01564/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 63 references that are in the map.
- First posted on arXiv 2 Feb 2021.

## Builds on (most cited first, 11 of 11)

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Safety Verification of Deep Neural Networks](https://mlsanity.com/paper/1610.06940/) (2016)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy](https://mlsanity.com/paper/1710.01711/) (2017)
- [Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges](https://mlsanity.com/paper/1905.04223/) (2019)
- [DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks](https://mlsanity.com/paper/1710.00486/) (2017)
- [DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing](https://mlsanity.com/paper/1802.02295/) (2018)
- [Quantifying Assurance in Learning-enabled Systems](https://mlsanity.com/paper/2006.10345/) (2020)
- [Towards Verifying Robustness of Neural Networks Against Semantic Perturbations](https://mlsanity.com/paper/1912.09533/) (2019)

## Built on by (most cited first, 30 of 42)

- [The Role of Explainability in Assuring Safety of Machine Learning in Healthcare](https://mlsanity.com/paper/2109.00520/) (2021)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System](https://mlsanity.com/paper/2204.07874/) (2022)
- [A Principles-based Ethics Assurance Argument Pattern for AI and Autonomous Systems](https://mlsanity.com/paper/2203.15370/) (2022)
- [Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testing](https://mlsanity.com/paper/2203.12026/) (2022)
- [AI Hazard Management: A framework for the systematic management of root causes for AI risks](https://mlsanity.com/paper/2310.16727/) (2023)
- [Towards Developing Safety Assurance Cases for Learning-Enabled Medical Cyber-Physical Systems](https://mlsanity.com/paper/2211.15413/) (2022)
- [AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms](https://mlsanity.com/paper/2302.10292/) (2023)
- [Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping](https://mlsanity.com/paper/2505.13182/) (2025)
- [Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems](https://mlsanity.com/paper/2510.21254/) (2025)
- [Creating a Safety Assurance Case for an ML Satellite-Based Wildfire Detection and Alert System](https://mlsanity.com/paper/2211.04530/) (2022)
- [Assessing Trustworthiness of Autonomous Systems](https://mlsanity.com/paper/2305.03411/) (2023)
- [Towards a safe MLOps Process for the Continuous Development and Safety Assurance of ML-based Systems in the Railway Domain](https://mlsanity.com/paper/2307.02867/) (2023)
- [KnowSafe: Combined Knowledge and Data Driven Hazard Mitigation in Artificial Pancreas Systems](https://mlsanity.com/paper/2311.07460/) (2023)
- [What's my role? Modelling responsibility for AI-based safety-critical systems](https://mlsanity.com/paper/2401.09459/) (2023)
- [The Open Autonomy Safety Case Framework](https://mlsanity.com/paper/2404.05444/) (2024)
- [Autonomous Robotic Swarms: A Corroborative Approach for Verification and Validation](https://mlsanity.com/paper/2407.15475/) (2024)
- [Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs](https://mlsanity.com/paper/2410.05304/) (2024)
- [Assuring the Safety of Reinforcement Learning Components: AMLAS-RL](https://mlsanity.com/paper/2507.08848/) (2025)
- [EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs](https://mlsanity.com/paper/2512.22240/) (2025)
- [Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials](https://mlsanity.com/paper/2603.12183/) (2026)
- [Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation](https://mlsanity.com/paper/2606.05660/) (2026)
- [An NCAP-like Safety Indicator for Self-Driving Cars](https://mlsanity.com/paper/2104.00859/) (2021)
- [Sample selection from a given dataset to validate machine learning models](https://mlsanity.com/paper/2104.14401/) (2021)
- [Safe AI -- How is this Possible?](https://mlsanity.com/paper/2201.10436/) (2022)
- [Evaluating Automated Driving Planner Robustness against Adversarial Influence](https://mlsanity.com/paper/2205.14697/) (2022)
- [Review of the AMLAS Methodology for Application in Healthcare](https://mlsanity.com/paper/2209.00421/) (2022)
- [A Trustworthiness Score to Evaluate DNN Predictions](https://mlsanity.com/paper/2301.08839/) (2023)
- [Operationalizing Assurance Cases for Data Scientists: A Showcase of Concepts and Tooling in the Context of Test Data Quality for Machine Learning](https://mlsanity.com/paper/2312.04917/) (2023)
- [Learning Run-time Safety Monitors for Machine Learning Components](https://mlsanity.com/paper/2406.16220/) (2024)

## Abstract (arXiv)

Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high degrees of autonomy and are safety critical. Establishing justified confidence in ML forms a core part of the safety case for these systems. In this document we introduce a methodology for the Assurance of Machine Learning for use in Autonomous Systems (AMLAS). AMLAS comprises a set of safety case patterns and a process for (1) systematically integrating safety assurance into the development of ML components and (2) for generating the evidence base for explicitly justifying the acceptable safety of these components when integrated into autonomous system applications.