mlsanityData to 14 Oct 2026

A Survey on AI Assurance

arXiv 2111.07505 ↗First posted 15 Nov 2021cs.AI cs.CYcited by 16

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) algorithms are increasingly providing decision making and operational support across multiple domains. AI includes a wide library of algorithms for different problems. One important notion for the adoption of AI algorithms into operational decision process is the concept of assurance. The literature on assurance, unfortunately, conceals its outcomes within a tangled landscape of conflicting approaches, driven by contradicting motivations, assumptions, and intuitions. Accordingly, albeit a rising and novel area, this manuscript provides a systematic review of research works that are relevant to AI assurance, between years 1985 - 2021, and aims to provide a structured alternative to the landscape. A new AI assurance definition is adopted and presented and assurance methods are contrasted and tabulated. Additionally, a ten-metric scoring system is developed and introduced to evaluate and compare existing methods. Lastly, in this manuscript, we provide foundational insights, discussions, future directions, a roadmap, and applicable recommendations for the development and deployment of AI assurance.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 47 of its 253 references that are in the map. First posted on arXiv 15 Nov 2021.

Builds on

47 of 253 references.

References · 47

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2016Concrete Problems in AI Safetycited by 1,642
  4. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  6. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  7. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  8. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
  9. 2015Doubly Robust Off-policy Value Evaluation for Reinforcement Learningcited by 339
  10. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 254
  11. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  12. 2020Explainable Reinforcement Learning: A Surveycited by 141
35 more
  1. 2020Explainability in Deep Reinforcement Learningcited by 97
  2. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  3. 2019The relationship between trust in AI and trustworthy machine learning technologiescited by 78
  4. 2018Adversarial Examples that Fool both Computer Vision and Time-Limited Humanscited by 73
  5. 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 70
  6. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  7. 2019Towards a Rigorous Evaluation of XAI Methods on Time Seriescited by 67
  8. 2019Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AIcited by 63
  9. 2020Trustworthy AIcited by 62
  10. 2019Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitationscited by 50
  11. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  12. 2019Dot-to-Dot: Explainable Hierarchical Reinforcement Learning for Robotic Manipulationcited by 35
  13. 2018AGI Safety Literature Reviewcited by 28
  14. 2017"Dave...I can assure you...that it's going to be all right..." -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationshipscited by 22
  15. 2018Automated Test Generation to Detect Individual Discrimination in AI Modelscited by 21
  16. 2020Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenariocited by 19
  17. 2016How to be Fair and Diverse?cited by 18
  18. 2019Detection of Face Recognition Adversarial Attackscited by 15
  19. 2021Foundations of data imbalance and solutions for a data democracycited by 11
  20. 2020Developing and Operating Artificial Intelligence Models in Trustworthy Autonomous Systemscited by 10
  21. 2019Enabling Explainable Fusion in Deep Learning with Fuzzy Integral Neural Networkscited by 7
  22. 2020Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Contextcited by 7
  23. 2020Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approachcited by 5
  24. 2018Towards Composable Bias Rating of AI Servicescited by 4
  25. 2021The application of artificial intelligence in software engineering: a review challenging conventional wisdomcited by 4
  26. 2016Limits to Verification and Validation of Agentic Behaviorcited by 3
  27. 2018The Role of Normware in Trustworthy and Explainable AIcited by 3
  28. 2020Generative Classifiers as a Basis for Trustworthy Image Classificationcited by 3
  29. 2020Online Safety Assurance for Deep Reinforcement Learningcited by 3
  30. 2019Using Quantifier Elimination to Enhance the Safety Assurance of Deep Neural Networkscited by 2
  31. 2020Locality Guided Neural Networks for Explainable Artificial Intelligencecited by 2
  32. 2020More Than Accuracy: Towards Trustworthy Machine Learning Interfaces for Object Recognitioncited by 2
  33. 2019Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanationcited by 1
  34. 2020A Structured Approach to Trustworthy Autonomous/Cognitive Systemscited by 1
  35. 2020Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023Rationalization for Explainable NLP: A Surveycited by 22
  2. 2022System Cards for AI-Based Decision-Making for Public Policycited by 13
  3. 2024Aligning Model Properties via Conformal Risk Controlcited by 7
  4. 2023Multi-variable Hard Physical Constraints for Climate Model Downscalingcited by 6
  5. 2023ExClaim: Explainable Neural Claim Verification Using Rationalizationcited by 4
  6. 2024Exploring Cross-model Neuronal Correlations in the Context of Predicting Model Performance and Generalizabilitycited by 3
  7. 2025On the Promise for Assurance of Differentiable Neurosymbolic Reasoning Paradigmscited by 3
  8. 2025Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interactioncited by 3
  9. 2021Outlier Detection using AI: A Surveycited by 1
  10. 2024A Review of Cybersecurity Incidents in the Food and Agriculture Sectorcited by 1
  11. 2024Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentationcited by 1
  12. 2021AI Assurance using Causal Inference: Application to Public Policycited by 0
4 more
  1. 2023Ovarian Cancer Data Analysis using Deep Learning: A Systematic Review from the Perspectives of Key Features of Data Analysis and AI Assurancecited by 0
  2. 2023MedISure: Towards Assuring Machine Learning-based Medical Image Classifiers using Mixup Boundary Analysiscited by 0
  3. 2023Advancing AI Audits for Enhanced AI Governancecited by 0
  4. 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levelscited by 0