Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence

Abstract

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 (AI 2 ) 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. Decision Making: Humans and Artificial Intelligence (AI)"Can I trust the recommendation of an AI agent?" This question is difficult to answer, especially if the decision at stake is complex and spans different spatial and temporal scales. Such difficulty is exacerbated when the outcomes of an AI-influenced decision may heighten existing risks to humans or introduce new risks altogether. Yet such high-stakes situations have become routine within the diverse systems that currently incorporate AI, like controls for chemical plants, defense systems, and health insurance rate determinations. Stakeholders must be prepared not only to configure AI and its enabling technologies for a given industry or activity, but also to have tools and methodologies to examine and recognize its failures, limitations, and needs for quality control at various stages of its development and implementation.The ultimate goal of AI is to provide users with actionable recommendations that meet both implicit and explicit goals of the decision makers and stakeholders. Recommendations generated from AI-based

Comparing the Emergence of Technical and Social Sciences Research in Artificial Intelligence

“…However, Figures 8, 9 suggest very little interdisciplinary engagement with these topics by AI researchers from both the social science and technical domains (The exception is the combination of risk assessment and networks that appear in the aforementioned graphs.) This "governance gap" in AI research exists despite growing concern by social science researchers about AI governance issues (Wachter et al, 2017;Winfield et al, 2018;Linkov et al, 2020). .…”

“…Advances in artificial intelligence (AI) have expanded its adoption in computer security of defense and financial systems, economics, education, and many other fields (Wachter et al, 2017;Winfield et al, 2018;Linkov et al, 2020). Emerging technologies like AI will eventually contend with regulatory pressure and public attention that may either hinder emerging technologies or stimulate their development.…”

“…For AI methods and algorithms, social scientists only recently have engaged substantially in discussion related to the field's implications and applications (Elsevier, 2018). For example, in computer security, researchers and developers have long focused in efficient machine learning algorithms to accurately detect cyber-attack or fraud, and only recently discussed issues related to privacy and bias of such AI algorithms (Linkov et al, 2020). Nevertheless, such AI literature in the social science domain has recently appeared (Selbst et al, 2017;Edwards and Veale, 2018), with scholars discussing AI's privacy and security, ethical, legal, economic, and other societal implications and applications (Ananny, 2016;Cath, 2018;Nemitz, 2018).…”

Multi-omics disease module detection with an explainable Greedy Decision Forest

“…While the rule-based approaches of early AI were comprehensible “glass box” approaches, at least in narrow domains, their weakness lay in dealing with the uncertainties of the real world 7 . Actionable Explainable AI (AXAI) is intended to help promote trust-building features by bringing decision analytic perspectives and human domain knowledge directly into the AI pipeline 8 , 9 .…”

Artificial intelligence for data-driven decision support systems in clinical cancer research: implementation guidelines

“…• Be transparent: the user needs to understand how it works and the power of the AI (explainability AI) [153]. Explainability concerns the ability to explain both the technical processes of an AI system and the related decisions.…”