Related Work
While formal AI incident research is relatively new, a number of people have been collecting what could be considered incidents. These include,
- Awesome Machine Learning Interpretability: AI Incident Tracker
- AI and Algorithimic Incidents and Controversies of Charlie Pownall
- Map of Helpful and Harmful AI
If you have an incident resource that could be added here, please contact us.
The following publications have been indexed by Google scholar as referencing the database itself, rather than solely individual incidents. Please contact us if your reference is missing.
Responsible AI Collaborative Research
Where needed to serve the broader safety and fairness communities, the Collab produces and sponsors research. Works to date include the following.
- The original research publication released at the public announcement of the AI Incident Database. All citations of this work will be added to this page.
McGregor, Sean. "Preventing repeated real world AI failures by cataloging incidents: The AI incident database." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35. No. 17. 2021. - A major update to the incident definitions and criteria as presented at the 2022 NeurIPS Workshop on Human-Centered AI.
McGregor, Sean, Kevin Paeth, and Khoa Lam. "Indexing AI Risks with Incidents, Issues, and Variants." arXiv preprint arXiv:2211.10384 (2022). - Our approach to reducing the uncertainty of incident causes when analyzing open source incident reports. Presented at SafeAI.
Pittaras, Nikiforos, and Sean McGregor. "A taxonomic system for failure cause analysis of open source AI incidents." arXiv preprint arXiv:2211.07280 (2022).
2023 (through February 24th)
- McGregor, Sean, and Jesse Hostetler. "Data-Centric Governance." arXiv preprint arXiv:2302.07872 (2023).
- NIST. Risk Management Playbook. 2023
2022
- Macrae, Carl. "Learning from the failure of autonomous and intelligent systems: Accidents, safety, and sociotechnical sources of risk." Risk analysis 42.9 (2022): 1999-2025.
- Felländer, Anna, et al. "Achieving a Data-driven Risk Assessment Methodology for Ethical AI." Digital Society 1.2 (2022): 13.
- Apruzzese, Giovanni, et al. "" Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice." arXiv preprint arXiv:2212.14315 (2022).
- Petersen, Eike, et al. "Responsible and regulatory conform machine learning for medicine: A survey of challenges and solutions." IEEE Access 10 (2022): 58375-58418.
- Schuett, Jonas. "Three lines of defense against risks from AI." arXiv preprint arXiv:2212.08364 (2022).
- Schiff, Daniel S. "Looking through a policy window with tinted glasses: Setting the agenda for US AI policy." Review of Policy Research.
- Neretin, Oleksii, and Vyacheslav Kharchenko. "Model for Describing Processes of AI Systems Vulnerabilities Collection and Analysis using Big Data Tools." 2022 12th International Conference on Dependable Systems, Services and Technologies (DESSERT). IEEE, 2022.
- Durso, Francis, et al. "Analyzing Failures in Artificial Intelligent Learning Systems (FAILS)." 2022 IEEE 29th Annual Software Technology Conference (STC). IEEE, 2022.
- Kassab, Mohamad, Joanna DeFranco, and Phillip Laplante. "Investigating Bugs in AI-Infused Systems: Analysis and Proposed Taxonomy." 2022 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW). IEEE, 2022.
- Braga, Juliao, et al. "Projeto para o desenvolvimento de um artigo sobre governança de algoritmos e dados." (2022).
- Secchi, Carlo, and Alessandro Gili. "Digitalisation for sustainable infrastructure: the road ahead." Digitalisation for sustainable infrastructure (2022): 1-326.
- Groza, Adrian, et al. "Elaborarea cadrului strategic nat, ional în domeniul inteligent, ei artificiale."
- Braga, Juliao, et al. "Project for the Development of a Paper on Algorithm and Data Governance." (2022). (Original Portuguese).
- NIST. Risk Management Playbook. 2022
- Shneiderman, Ben. Human-Centered AI. Oxford University Press, 2022.
- Schwartz, Reva, et al. "Towards a Standard for Identifying and Managing Bias in Artificial Intelligence." (2022).
- McGrath, Quintin et al. An Enterprise Risk Management Framework to Design Pro-Ethical AI Solutions." University of South Florida. (2022).
- Nor, Ahmad Kamal Mohd, et al. "Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies." (2022).
- Xie, Xuan, Kristian Kersting, and Daniel Neider. "Neuro-Symbolic Verification of Deep Neural Networks." arXiv preprint arXiv:2203.00938 (2022).
- Hundt, Andrew, et al. "Robots Enact Malignant Stereotypes." 2022 ACM Conference on Fairness, Accountability, and Transparency. 2022.
- Tidjon, Lionel Nganyewou, and Foutse Khomh. "Threat Assessment in Machine Learning based Systems." arXiv preprint arXiv:2207.00091 (2022).
- Naja, Iman, et al. "Using Knowledge Graphs to Unlock Practical Collection, Integration, and Audit of AI Accountability Information." IEEE Access 10 (2022): 74383-74411.
- Cinà, Antonio Emanuele, et al. "Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning." arXiv preprint arXiv:2205.01992 (2022).
- Schröder, Tim, and Michael Schulz. "Monitoring machine learning models: A categorization of challenges and methods." Data Science and Management (2022).
- Corea, Francesco, et al. "A principle-based approach to AI: the case for European Union and Italy." AI & SOCIETY (2022): 1-15.
- Carmichael, Zachariah, and Walter J. Scheirer. "Unfooling Perturbation-Based Post Hoc Explainers." arXiv preprint arXiv:2205.14772 (2022).
- Wei, Mengyi, and Zhixuan Zhou. "AI Ethics Issues in Real World: Evidence from AI Incident Database." arXiv preprint arXiv:2206.07635 (2022).
- Petersen, Eike, et al. "Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions." IEEE Access (2022).
- Karunagaran, Surya, Ana Lucic, and Christine Custis. "XAI Toolsheet: Towards A Documentation Framework for XAI Tools."
- Paudel, Shreyasha, and Aatiz Ghimire. "AI Ethics Survey in Nepal."
- Ferguson, Ryan. "Transform Your Risk Processes Using Neural Networks."
- Fujitsu Corporation. "AI Ethics Impact Assessment Casebook," 2022
- Shneiderman, Ben and Du, Mengnan. "Human-Centered AI: Tools" 2022
- Salih, Salih. "Understanding Machine Learning Interpretability." Medium. 2022
- Garner, Carrie. "Creating Transformative and Trustworthy AI Systems Requires a Community Effort." Software Engineering Institute. 2022
- Weissinger, Laurin, AI, Complexity, and Regulation (February 14, 2022). The Oxford Handbook of AI Governance
2021
- Arnold, Z., Toner, H., CSET Policy. "AI Accidents: An Emerging Threat." (2021).
- Aliman, Nadisha-Marie, Leon Kester, and Roman Yampolskiy. "Transdisciplinary AI Observatory—Retrospective Analyses and Future-Oriented Contradistinctions." Philosophies 6.1 (2021): 6.
- Falco, Gregory, and Leilani H. Gilpin. "A stress testing framework for autonomous system verification and validation (v&v)." 2021 IEEE International Conference on Autonomous Systems (ICAS). IEEE, 2021.
- Petersen, Eike, et al. "Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Technical Challenges and Solutions." arXiv preprint arXiv:2107.09546 (2021).
- John-Mathews, Jean-Marie. AI ethics in practice, challenges and limitations. Diss. Université Paris-Saclay, 2021.
- Macrae, Carl. "Learning from the Failure of Autonomous and Intelligent Systems: Accidents, Safety and Sociotechnical Sources of Risk." Safety and Sociotechnical Sources of Risk (June 4, 2021) (2021).
- Hong, Matthew K., et al. "Planning for Natural Language Failures with the AI Playbook." Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 2021.
- Ruohonen, Jukka. "A Review of Product Safety Regulations in the European Union." arXiv preprint arXiv:2102.03679 (2021).
- Kalin, Josh, David Noever, and Matthew Ciolino. "A Modified Drake Equation for Assessing Adversarial Risk to Machine Learning Models." arXiv preprint arXiv:2103.02718 (2021).
- Aliman, Nadisha Marie, and Leon Kester. "Epistemic defenses against scientific and empirical adversarial AI attacks." CEUR Workshop Proceedings. Vol. 2916. CEUR WS, 2021.
- John-Mathews, Jean-Marie. L’Éthique de l’Intelligence Artificielle en Pratique. Enjeux et Limites. Diss. université Paris-Saclay, 2021.
- Smith, Catherine. "Automating intellectual freedom: Artificial intelligence, bias, and the information landscape." IFLA Journal (2021): 03400352211057145
If you have a scholarly work that should be added here, please contact us.