A Survey on AI Assurance

Abstract

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.

This paper is published at Springer's Journal of Big Data

References in corpus (11)

• Explaining and Harnessing Adversarial Examples
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI
• Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing
• Enabling Explainable Fusion in Deep Learning with Fuzzy Integral Neural Networks
• An Inductive Synthesis Framework for Verifiable Reinforcement Learning
• Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach
• More Than Accuracy: Towards Trustworthy Machine Learning Interfaces for Object Recognition
• A Structured Approach to Trustworthy Autonomous/Cognitive Systems
• Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanation
• Locality Guided Neural Networks for Explainable Artificial Intelligence

Cited by in corpus (5)

• Rationalization for Explainable NLP: A Survey
• Empirically Measuring Transfer Distance for System Design and Operation
• ExClaim: Explainable Neural Claim Verification Using Rationalization
• Probabilistic modelling and safety assurance of an agriculture robot providing light-treatment
• A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle