mlsanityData to 13 Oct 2026

Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation

arXiv 2305.02231 ↗First posted 2 May 2023cs.CY cs.AI cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and a social perspective. However, attaining truly trustworthy AI concerns a wider vision that comprises the trustworthiness of all processes and actors that are part of the system's life cycle, and considers previous aspects from different lenses. A more holistic vision contemplates four essential axes: the global principles for ethical use and development of AI-based systems, a philosophical take on AI ethics, a risk-based approach to AI regulation, and the mentioned pillars and requirements. The seven requirements (human agency and oversight; robustness and safety; privacy and data governance; transparency; diversity, non-discrimination and fairness; societal and environmental wellbeing; and accountability) are analyzed from a triple perspective: What each requirement for trustworthy AI is, Why it is needed, and How each requirement can be implemented in practice. On the other hand, a practical approach to implement trustworthy AI systems allows defining the concept of responsibility of AI-based systems facing the law, through a given auditing process. Therefore, a responsible AI system is the resulting notion we introduce in this work, and a concept of utmost necessity that can be realized through auditing processes, subject to the challenges posed by the use of regulatory sandboxes. Our multidisciplinary vision of trustworthy AI culminates in a debate on the diverging views published lately about the future of AI. Our reflections in this matter conclude that regulation is a key for reaching a consensus among these views, and that trustworthy and responsible AI systems will be crucial for the present and future of our society.

Key facts. Cited by 60 papers in the map (data through 13 Oct 2026). Builds on 56 of its 163 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

56 of 163 references.

References · 56

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,180
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,339
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,055
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,284
  5. 2016Deep Learning with Differential Privacycited by 2,718
  6. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,915
  7. 2016Concrete Problems in AI Safetycited by 1,614
  8. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,547
  9. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,248
  10. 2019Machine Unlearningcited by 1,056
  11. 2019Towards Federated Learning at Scale: System Designcited by 830
  12. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 817
38 more
  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 799
  2. 2016The Mythos of Model Interpretabilitycited by 718
  3. 2020Aligning AI With Shared Human Valuescited by 717
  4. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  5. 2019Green AIcited by 623
  6. 2019Quantifying the Carbon Emissions of Machine Learningcited by 519
  7. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  8. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  9. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 298
  10. 2021Unsolved Problems in ML Safetycited by 291
  11. 2019Tackling Climate Change with Machine Learningcited by 265
  12. 2018Metrics for Explainable AI: Challenges and Prospectscited by 258
  13. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  14. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 193
  15. 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 183
  16. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  17. 2017Quality and Diversity Optimization: A Unifying Modular Frameworkcited by 111
  18. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 92
  19. 2019Fairwashing: the risk of rationalizationcited by 81
  20. 2017What Does Explainable AI Really Mean? A New Conceptualization of Perspectivescited by 72
  21. 2019Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanationscited by 63
  22. 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
  23. 2020A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutionscited by 32
  24. 2019Explaining Deep Classification of Time-Series Data with Learned Prototypescited by 30
  25. 2021EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use casecited by 30
  26. 2019Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfercited by 24
  27. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 23
  28. 2020Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacycited by 22
  29. 2021Characterizing the risk of fairwashingcited by 21
  30. 2021Conformity Assessments and Post-market Monitoring: A Guide to the Role of Auditing in the Proposed European AI Regulationcited by 19
  31. 2022CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanationscited by 16
  32. 2022Attribution-based XAI Methods in Computer Vision: A Reviewcited by 16
  33. 2021ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNscited by 15
  34. 2021Roadmap of Designing Cognitive Metrics for Explainable Artificial Intelligence (XAI)cited by 13
  35. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  36. 2023Towards Concrete and Connected AI Risk Assessment (C2AIRA): A Systematic Mapping Studycited by 9
  37. 2021A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Actcited by 8
  38. 2022Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledgecited by 6

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 3; 2024: 22; 2025: 23; 2026: 12.

60 papers.

Sort:

By area:

  1. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 127
  2. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 124
  3. 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
  4. 2024Secret Use of Large Language Model (LLM)cited by 9
  5. 2024Leveraging Generative AI for Urban Digital Twins: A Scoping Review on the Autonomous Generation of Urban Data, Scenarios, Designs, and 3D City Models for Smart City Advancementcited by 7
  6. 2024Fairness-Aware Meta-Learning via Nash Bargainingcited by 6
  7. 2025Position: Bridge the Gaps between Machine Unlearning and AI Regulationcited by 6
  8. 2024An Interpretable Client Decision Tree Aggregation process for Federated Learningcited by 5
  9. 2024LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architecturescited by 5
  10. 2025Leveraging Intermediate Representations for Better Out-of-Distribution Detectioncited by 5
  11. 2025A Framework for Responsible AI Systems: Building Societal Trust through Domain Definition, Trustworthy AI Design, Auditability, Accountability, and Governancecited by 5
  12. 2024FLEX: FLEXible Federated Learning Frameworkcited by 4
38 more
  1. 2025World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Childcited by 4
  2. 2025From monoliths to modules: Decomposing transducers for efficient world modellingcited by 4
  3. 2024Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systemscited by 3
  4. 2024Human-Centric eXplainable AI in Educationcited by 3
  5. 2025The Algorithmic State Architecture (ASA): An Integrated Framework for AI-Enabled Governmentcited by 3
  6. 2025AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretabilitycited by 3
  7. 2025A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoptioncited by 3
  8. 2026Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyondcited by 3
  9. 2024Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive Biascited by 2
  10. 2024Integrating ESG and AI: A Comprehensive Responsible AI Assessment Frameworkcited by 2
  11. 2024Comprehensive Equity Index (CEI): Definition and Application to Bias Evaluation in Biometricscited by 2
  12. 2025Adaptive AI decision interface for autonomous electronic material discoverycited by 2
  13. 2025Artificial Intelligence for Atmospheric Sciences: A Research Roadmapcited by 2
  14. 2025TechOps: Technical Documentation Templates for the AI Actcited by 2
  15. 2026Membership Inference Test: Auditing Training Data in Object Classification Modelscited by 2
  16. 2023Trustworthy, responsible, ethical AI in manufacturing and supply chains: synthesis and emerging research questionscited by 1
  17. 2023General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governancecited by 1
  18. 2024Overlap Number of Balls Model-Agnostic CounterFactuals (ONB-MACF): A Data-Morphology-based Counterfactual Generation Method for Trustworthy Artificial Intelligencecited by 1
  19. 2024Global AI Governance in Healthcare: A Cross-Jurisdictional Regulatory Analysiscited by 1
  20. 2024Evolutionary Computation for the Design and Enrichment of General-Purpose Artificial Intelligence Systems: Survey and Prospectscited by 1
  21. 2025CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMscited by 1
  22. 2025Responsible AI Adoption in the Public Sector: A Data-Centric Taxonomy of AI Adoption Challengescited by 1
  23. 2026Trustworthy AI Posture (TAIP): A Framework for Continuous AI Assurance of Agentic Systems at Horizontal and Vertical scalecited by 1
  24. 2026Hierarchically Robust Zero-shot Vision-language Modelscited by 1
  25. 2024Connecting Algorithmic Fairness to Quality Dimensions in Machine Learning in Official Statistics and Survey Productioncited by 0
  26. 2024Practical Guide for Causal Pathways and Sub-group Disparity Analysiscited by 0
  27. 2024AI Governance in Higher Education: Case Studies of Guidance at Big Ten Universitiescited by 0
  28. 2024RAB2-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clientscited by 0
  29. 2024Standardization Trends on Safety and Trustworthiness Technology for Advanced AIcited by 0
  30. 2024On the Inherent Robustness of One-Stage Object Detection against Out-of-Distribution Datacited by 0
  31. 2025Privacy in Responsible AI: Approaches to Facial Recognition from Cloud Providerscited by 0
  32. 2025Am I Being Treated Fairly? A Conceptual Framework for Individuals to Ascertain Fairnesscited by 0
  33. 2025Aligning Trustworthy AI with Democracy: A Dual Taxonomy of Opportunities and Riskscited by 0
  34. 2025AI and Remote Sensing for Resilient and Sustainable Built Environments: A Review of Current Methods, Open Data and Future Directionscited by 0
  35. 2025From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0cited by 0
  36. 2025Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trustcited by 0
  37. 2025Structured AI Decision-Making in Disaster Managementcited by 0
  38. 2025An Adaptive Responsible AI Governance Framework for Decentralized Organizationscited by 0

50 most cited of 60 All 60 (JSON)