mlsanityData to 7 Oct 2026

Understanding and Avoiding AI Failures: A Practical Guide

arXiv 2104.12582 ↗First posted 22 Apr 2021cs.CY cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated with AI applications. In addition, we also use AI safety principles to quantify the unique risks of increased intelligence and human-like qualities in AI. Together, these two fields give a more complete picture of the risks of contemporary AI. By focusing on system properties near accidents instead of seeking a root cause of accidents, we identify where attention should be paid to safety for current generation AI systems.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 72 references that are in the map. First posted on arXiv 22 Apr 2021.

Builds on

20 of 72 references.

References · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2016Concrete Problems in AI Safetycited by 1,582
  5. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  6. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  7. 2017One pixel attack for fooling deep neural networkscited by 579
  8. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  9. 2016Cooperative Inverse Reinforcement Learningcited by 298
  10. 2017Inverse Reward Designcited by 246
  11. 2017AI Safety Gridworldscited by 108
  12. 2018The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communitiescited by 78
8 more
  1. 2018Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failurecited by 49
  2. 2014Safe Exploration of State and Action Spaces in Reinforcement Learningcited by 37
  3. 2018Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Ataricited by 26
  4. 2019Global AI Ethics: A Review of the Social Impacts and Ethical Implications of Artificial Intelligencecited by 21
  5. 2021Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agentscited by 6
  6. 2019Safe Artificial General Intelligence via Distributed Ledger Technologycited by 1
  7. 2019Classification Schemas for Artificial Intelligence Failurescited by 1
  8. 2020Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recoverycited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 1; 2025: 1.

6 papers.

  1. 2022Logic-Based Explainability in Machine Learningcited by 47
  2. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  3. 2022Establishing Meta-Decision-Making for AI: An Ontology of Relevance, Representation and Reasoningcited by 2
  4. 2021AI Risk Skepticismcited by 1
  5. 2024Reporting Risks in AI-based Assistive Technology Research: A Systematic Reviewcited by 0
  6. 2025The Stories We Govern By: AI, Risk, and the Power of Imaginariescited by 0