A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities

• URL: http://arxiv.org/abs/2210.08906v2
• Date: Wed, 19 Oct 2022 07:37:47 GMT
• Title: A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
• Authors: Andrea Tocchetti, Lorenzo Corti, Agathe Balayn, Mireia Yurrita, Philip Lippmann, Marco Brambilla, and Jie Yang
• Abstract summary: Robustness of Artificial Intelligence (AI) systems remains elusive and constitutes a key issue that impedes large-scale adoption. We introduce three concepts to organize and describe the literature both from a fundamental and applied point of view. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge humans can provide.
• Score: 8.17368686298331
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Robustness has been studied in many domains of AI, yet with different interpretations across domains and contexts. In this work, we systematically survey the recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: 1) robustness by methods and approaches in different phases of the machine learning pipeline; 2) robustness for specific model architectures, tasks, and systems; and in addition, 3) robustness assessment methodologies and insights, particularly the trade-offs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge humans can provide, and discuss the need for better understanding practices and developing supportive tools in the future.

Related papers

• Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions [101.67121669727354]
  Recent advancements in AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. The lack of clarified definitions and scopes of human-AI alignment poses a significant obstacle, hampering collaborative efforts across research domains to achieve this alignment. We introduce a systematic review of over 400 papers published between 2019 and January 2024, spanning multiple domains such as Human-Computer Interaction (HCI), Natural Language Processing (NLP), Machine Learning (ML)
  arXiv  Detail & Related papers  (2024-06-13T16:03:25Z)
• Explainable Interface for Human-Autonomy Teaming: A Survey [12.26178592621411]
  This paper conducts a thoughtful study on the underexplored domain of Explainable Interface (EI) in HAT systems. We explore the design, development, and evaluation of EI within XAI-enhanced HAT systems. We contribute to a novel framework for EI, addressing the unique challenges in HAT.
  arXiv  Detail & Related papers  (2024-05-04T06:35:38Z)
• Position Paper: Agent AI Towards a Holistic Intelligence [53.35971598180146]
  We emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. In this paper, we propose a novel large action model to achieve embodied intelligent behavior, the Agent Foundation Model.
  arXiv  Detail & Related papers  (2024-02-28T16:09:56Z)
• Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness [53.91018508439669]
  The study explores the complexities of integrating Artificial Intelligence into Autonomous Vehicles (AVs) It examines the challenges introduced by AI components and the impact on testing procedures. The paper identifies significant challenges and suggests future directions for research and development of AI in AV technology.
  arXiv  Detail & Related papers  (2024-02-21T08:29:42Z)
• A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research [23.966640472958105]
  This paper presents a systematic literature review of approaches that aim to improve the explainability of AI models within the context of Software Engineering. We aim to summarize the SE tasks where XAI techniques have shown success to date; (2) classify and analyze different XAI techniques; and (3) investigate existing evaluation approaches.
  arXiv  Detail & Related papers  (2024-01-26T03:20:40Z)
• On the Multiple Roles of Ontologies in Explainable AI [0.32634122554913997]
  This paper discusses the different roles that explicit knowledge, in particular, can play in Explainable AI. We consider three main perspectives in which reference modelling, common-sense reasoning, and knowledge refinement and complexity management.
  arXiv  Detail & Related papers  (2023-11-08T15:57:26Z)
• Predictable Artificial Intelligence [77.1127726638209]
  This paper introduces the ideas and challenges of Predictable AI. It explores the ways in which we can anticipate key validity indicators of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems.
  arXiv  Detail & Related papers  (2023-10-09T21:36:21Z)
• Understanding the Application of Utility Theory in Robotics and Artificial Intelligence: A Survey [5.168741399695988]
  The utility is a unifying concept in economics, game theory, and operations research, even in the Robotics and AI field. This paper introduces a utility-orient needs paradigm to describe and evaluate inter and outer relationships among agents' interactions.
  arXiv  Detail & Related papers  (2023-06-15T18:55:48Z)
• Explainable Deep Reinforcement Learning: State of the Art and Challenges [1.005130974691351]
  Interpretability, explainability and transparency are key issues to introducing Artificial Intelligence methods in many critical domains. This article provides a review of state of the art methods for explainable deep reinforcement learning methods.
  arXiv  Detail & Related papers  (2023-01-24T11:41:25Z)
• Active Inference in Robotics and Artificial Agents: Survey and Challenges [51.29077770446286]
  We review the state-of-the-art theory and implementations of active inference for state-estimation, control, planning and learning. We showcase relevant experiments that illustrate its potential in terms of adaptation, generalization and robustness.
  arXiv  Detail & Related papers  (2021-12-03T12:10:26Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

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.