mlsanityData to 14 Oct 2026

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

arXiv 2102.01564 ↗First posted 2 Feb 2021cs.LG cs.AIcited by 42

Not on the map. Why?

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.

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

11 of 63 references.

References · 11

  1. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  2. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  3. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  4. 2016Safety Verification of Deep Neural Networkscited by 263
  5. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
  6. 2017Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathycited by 44
  7. 2019Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challengescited by 39
  8. 2017DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networkscited by 20
  9. 2018DeepRoad: GAN-based Metamorphic Autonomous Driving System Testingcited by 9
  10. 2020Quantifying Assurance in Learning-enabled Systemscited by 4
  11. 2019Towards Verifying Robustness of Neural Networks Against Semantic Perturbationscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 8; 2024: 6; 2025: 5; 2026: 11.

42 papers.

Sort:

By area:

  1. 2021The Role of Explainability in Assuring Safety of Machine Learning in Healthcarecited by 26
  2. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
  3. 2022Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake Systemcited by 14
  4. 2022A Principles-based Ethics Assurance Argument Pattern for AI and Autonomous Systemscited by 6
  5. 2022Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testingcited by 4
  6. 2023AI Hazard Management: A framework for the systematic management of root causes for AI riskscited by 3
  7. 2022Towards Developing Safety Assurance Cases for Learning-Enabled Medical Cyber-Physical Systemscited by 2
  8. 2023AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarmscited by 2
  9. 2025Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mappingcited by 2
  10. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  11. 2022Creating a Safety Assurance Case for an ML Satellite-Based Wildfire Detection and Alert Systemcited by 1
  12. 2023Assessing Trustworthiness of Autonomous Systemscited by 1
30 more
  1. 2023Towards a safe MLOps Process for the Continuous Development and Safety Assurance of ML-based Systems in the Railway Domaincited by 1
  2. 2023KnowSafe: Combined Knowledge and Data Driven Hazard Mitigation in Artificial Pancreas Systemscited by 1
  3. 2023What's my role? Modelling responsibility for AI-based safety-critical systemscited by 1
  4. 2024The Open Autonomy Safety Case Frameworkcited by 1
  5. 2024Autonomous Robotic Swarms: A Corroborative Approach for Verification and Validationcited by 1
  6. 2024Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMscited by 1
  7. 2025Assuring the Safety of Reinforcement Learning Components: AMLAS-RLcited by 1
  8. 2025EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runscited by 1
  9. 2026Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentialscited by 1
  10. 2026Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulationcited by 1
  11. 2021An NCAP-like Safety Indicator for Self-Driving Carscited by 0
  12. 2021Sample selection from a given dataset to validate machine learning modelscited by 0
  13. 2022Safe AI -- How is this Possible?cited by 0
  14. 2022Evaluating Automated Driving Planner Robustness against Adversarial Influencecited by 0
  15. 2022Review of the AMLAS Methodology for Application in Healthcarecited by 0
  16. 2023A Trustworthiness Score to Evaluate DNN Predictionscited by 0
  17. 2023Operationalizing Assurance Cases for Data Scientists: A Showcase of Concepts and Tooling in the Context of Test Data Quality for Machine Learningcited by 0
  18. 2024Learning Run-time Safety Monitors for Machine Learning Componentscited by 0
  19. 2024A SAT-based approach to rigorous verification of Bayesian networkscited by 0
  20. 2024Landscape of AI safety concerns -- A methodology to support safety assurance for AI-based autonomous systemscited by 0
  21. 2025A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practicecited by 0
  22. 2026Safety Case Patterns for VLA-based driving systems: Insights from SimLingocited by 0
  23. 2026Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Frameworkcited by 0
  24. 2026Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safetycited by 0
  25. 2026I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contextscited by 0
  26. 2026Engineering Reliable Autonomous Systems: Challenges and Solutionscited by 0
  27. 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levelscited by 0
  28. 2026Beyond Component Testing: Validating Agentic AI Systemscited by 0
  29. 2026Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agentscited by 0
  30. 2026Dependable AI-Assisted Engineering: A Formal Framework for AI Participation and Assurance in Safety-Critical Workflowscited by 0