mlsanityData to 7 Oct 2026

Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database

arXiv 2011.08512 ↗First posted 17 Nov 2020cs.CY cs.SEcited by 95

Not on the map. Why?

Abstract (arXiv)

Mature industrial sectors (e.g., aviation) collect their real world failures in incident databases to inform safety improvements. Intelligent systems currently cause real world harms without a collective memory of their failings. As a result, companies repeatedly make the same mistakes in the design, development, and deployment of intelligent systems. A collection of intelligent system failures experienced in the real world (i.e., incidents) is needed to ensure intelligent systems benefit people and society. The AI Incident Database is an incident collection initiated by an industrial/non-profit cooperative to enable AI incident avoidance and mitigation. The database supports a variety of research and development use cases with faceted and full text search on more than 1,000 incident reports archived to date.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 11; 2023: 10; 2024: 19; 2025: 28; 2026: 25.

95 papers.

Sort:

By area:

  1. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  2. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 55
  3. 2022Logic-Based Explainability in Machine Learningcited by 47
  4. 2024Farsight: Fostering Responsible AI Awareness During AI Application Prototypingcited by 28
  5. 2026The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemscited by 27
  6. 2022Neuro-Symbolic Verification of Deep Neural Networkscited by 21
  7. 2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harmscited by 19
  8. 2023Pixel-Grounded Prototypical Part Networkscited by 18
  9. 2024Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generatorscited by 18
  10. 2022AI Ethics Issues in Real World: Evidence from AI Incident Databasecited by 14
  11. 2022Robots Enact Malignant Stereotypescited by 14
  12. 2025The AI Agent Indexcited by 14
38 more
  1. 2022Unfooling Perturbation-Based Post Hoc Explainerscited by 12
  2. 2023fAIlureNotes: Supporting Designers in Understanding the Limits of AI Models for Computer Vision Taskscited by 10
  3. 2024Responsible Reporting for Frontier AI Developmentcited by 10
  4. 2022Threat Assessment in Machine Learning based Systemscited by 9
  5. 2022A taxonomic system for failure cause analysis of open source AI incidentscited by 9
  6. 2023Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Erniecited by 8
  7. 2023The AI Incident Database as an Educational Tool to Raise Awareness of AI Harms: A Classroom Exploration of Efficacy, Limitations, & Future Improvementscited by 8
  8. 2021Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutionscited by 7
  9. 2025In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AIcited by 7
  10. 2025RealHarm: A Collection of Real-World Language Model Application Failurescited by 7
  11. 2024BLIP: Facilitating the Exploration of Undesirable Consequences of Digital Technologiescited by 6
  12. 2024The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AIcited by 6
  13. 2025Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Modelscited by 6
  14. 2024Lessons for Editors of AI Incidents from the AI Incident Databasecited by 5
  15. 2024To Err is AI : A Case Study Informing LLM Flaw Reporting Practicescited by 5
  16. 2025Standardised schema and taxonomy for AI incident databases in critical digital infrastructurecited by 5
  17. 2025Stakeholder Participation for Responsible AI Development: Disconnects Between Guidance and Current Practicecited by 5
  18. 2022Indexing AI Risks with Incidents, Issues, and Variantscited by 4
  19. 2023AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosurescited by 4
  20. 2025Advancing Trustworthy AI for Sustainable Development: Recommendations for Standardising AI Incident Reportingcited by 4
  21. 2025The Unified Control Framework: Establishing a Common Foundation for Enterprise AI Governance, Risk Management and Regulatory Compliancecited by 4
  22. 2022Artificial intelligence in government: Concepts, standards, and a unified frameworkcited by 3
  23. 2023An HCAI Methodological Framework (HCAI-MF): Putting It Into Action to Enable Human-Centered AIcited by 3
  24. 2024Investigating Algorithm Review Boards for Organizational Responsible Artificial Intelligence Governancecited by 3
  25. 2024Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairnesscited by 3
  26. 2024JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensemblescited by 3
  27. 2025From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harmscited by 3
  28. 2025The Backfiring Effect of Weak AI Safety Regulationcited by 3
  29. 2025In-Context Adaptation to Concept Drift for Learned Database Operationscited by 3
  30. 2023How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?cited by 2
  31. 2023Assessing AI Impact Assessments: A Classroom Studycited by 2
  32. 2024Integrating ESG and AI: A Comprehensive Responsible AI Assessment Frameworkcited by 2
  33. 2024AI for All: Identifying AI incidents Related to Diversity and Inclusioncited by 2
  34. 2025Documenting Deployment with Fabric: A Repository of Real-World AI Governancecited by 2
  35. 2025The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harmscited by 2
  36. 2025AI Harmonics: a human-centric and harms severity-adaptive AI risk assessment frameworkcited by 2
  37. 2025A five-layer framework for AI governance: integrating regulation, standards, and certificationcited by 2
  38. 2025Psychological and behavioural responses in human-agent vs. human-human interactions: a systematic review and meta-analysiscited by 2

50 most cited of 95 All 95 (JSON)