# Cybertrust: From Explainable to Actionable and Interpretable AI (AI2)

arXiv: https://arxiv.org/abs/2201.11117 · HTML: https://mlsanity.com/paper/2201.11117/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 26 Jan 2022.

## Builds on (most cited first, 2 of 2)

- [Sanity Checks for Saliency Metrics](https://mlsanity.com/paper/1912.01451/) (2019)
- [Autonomous Intelligent Cyber-defense Agent (AICA) Reference Architecture. Release 2.0](https://mlsanity.com/paper/1803.10664/) (2018)

## Built on by (most cited first, 1 of 1)

- [Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations](https://mlsanity.com/paper/2302.10671/) (2023)

## Abstract (arXiv)

To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some understanding of AI operations can support predictability, but forcing AI to explain itself risks constraining AI capabilities to only those reconcilable with human cognition. We argue that AI systems should be designed with features that build trust by bringing decision-analytic perspectives and formal tools into AI. Instead of trying to achieve explainable AI, we should develop interpretable and actionable AI. Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. In doing so, it will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making and ensure broad benefits from deploying and advancing its computational capabilities.