Survey of Trustworthy AI: A Meta Decision of AI
- URL: http://arxiv.org/abs/2306.00380v2
- Date: Mon, 12 Jun 2023 06:04:32 GMT
- Title: Survey of Trustworthy AI: A Meta Decision of AI
- Authors: Caesar Wu, Yuan-Fang Lib, and Pascal Bouvry
- Abstract summary: Trusting an opaque system involves deciding on the level of Trustworthy AI (TAI)
To underpin these domains, we create ten dimensions to measure trust: explainability/transparency, fairness/diversity, generalizability, privacy, data governance, safety/robustness, accountability, reliability, and sustainability.
- Score: 0.41292255339309647
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: When making strategic decisions, we are often confronted with overwhelming
information to process. The situation can be further complicated when some
pieces of evidence are contradicted each other or paradoxical. The challenge
then becomes how to determine which information is useful and which ones should
be eliminated. This process is known as meta-decision. Likewise, when it comes
to using Artificial Intelligence (AI) systems for strategic decision-making,
placing trust in the AI itself becomes a meta-decision, given that many AI
systems are viewed as opaque "black boxes" that process large amounts of data.
Trusting an opaque system involves deciding on the level of Trustworthy AI
(TAI). We propose a new approach to address this issue by introducing a novel
taxonomy or framework of TAI, which encompasses three crucial domains:
articulate, authentic, and basic for different levels of trust. To underpin
these domains, we create ten dimensions to measure trust:
explainability/transparency, fairness/diversity, generalizability, privacy,
data governance, safety/robustness, accountability, reproducibility,
reliability, and sustainability. We aim to use this taxonomy to conduct a
comprehensive survey and explore different TAI approaches from a strategic
decision-making perspective.
Related papers
- Imagining and building wise machines: The centrality of AI metacognition [78.76893632793497]
We argue that shortcomings stem from one overarching failure: AI systems lack wisdom.
While AI research has focused on task-level strategies, metacognition is underdeveloped in AI systems.
We propose that integrating metacognitive capabilities into AI systems is crucial for enhancing their robustness, explainability, cooperation, and safety.
arXiv Detail & Related papers (2024-11-04T18:10:10Z) - Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks.
We show that the learned AI control system demonstrates robustness against adversarial tampering.
In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
arXiv Detail & Related papers (2024-07-03T15:38:57Z) - Trustworthy AI: Deciding What to Decide [41.10597843436572]
We propose a novel framework of Trustworthy AI (TAI) encompassing crucial components of AI.
We aim to use this framework to conduct the TAI experiments by quantitive and qualitative research methods.
We formulate an optimal prediction model for applying the strategic investment decision of credit default swaps (CDS) in the technology sector.
arXiv Detail & Related papers (2023-11-21T13:43:58Z) - Trust, Accountability, and Autonomy in Knowledge Graph-based AI for
Self-determination [1.4305544869388402]
Knowledge Graphs (KGs) have emerged as fundamental platforms for powering intelligent decision-making.
The integration of KGs with neuronal learning is currently a topic of active research.
This paper conceptualises the foundational topics and research pillars to support KG-based AI for self-determination.
arXiv Detail & Related papers (2023-10-30T12:51:52Z) - Never trust, always verify : a roadmap for Trustworthy AI? [12.031113181911627]
We examine trust in the context of AI-based systems to understand what it means for an AI system to be trustworthy.
We suggest a trust (resp. zero-trust) model for AI and suggest a set of properties that should be satisfied to ensure the trustworthiness of AI systems.
arXiv Detail & Related papers (2022-06-23T21:13:10Z) - Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations.
It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
arXiv Detail & Related papers (2022-01-26T18:53:09Z) - Knowledge-intensive Language Understanding for Explainable AI [9.541228711585886]
How AI-led decisions are made and what determining factors were included are crucial to understand.
It is critical to have human-centered explanations that are directly related to decision-making.
It is necessary to involve explicit domain knowledge that humans understand and use.
arXiv Detail & Related papers (2021-08-02T21:12:30Z) - Trustworthy AI [75.99046162669997]
Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations.
We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
arXiv Detail & Related papers (2020-11-02T20:04:18Z) - Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and
Goals of Human Trust in AI [55.4046755826066]
We discuss a model of trust inspired by, but not identical to, sociology's interpersonal trust (i.e., trust between people)
We incorporate a formalization of 'contractual trust', such that trust between a user and an AI is trust that some implicit or explicit contract will hold.
We discuss how to design trustworthy AI, how to evaluate whether trust has manifested, and whether it is warranted.
arXiv Detail & Related papers (2020-10-15T03:07:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.