mlsanityData to 7 Oct 2026

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

arXiv 2406.17864 ↗First posted 25 Jun 2024cs.CY cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative AI safety evaluation. We identify 314 unique risk categories organized into a four-tiered taxonomy. At the highest level, this taxonomy encompasses System & Operational Risks, Content Safety Risks, Societal Risks, and Legal & Rights Risks. The taxonomy establishes connections between various descriptions and approaches to risk, highlighting the overlaps and discrepancies between public and private sector conceptions of risk. By providing this unified framework, we aim to advance AI safety through information sharing across sectors and the promotion of best practices in risk mitigation for generative AI models and systems.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 13 of its 61 references that are in the map. First posted on arXiv 25 Jun 2024.

Builds on

13 of 61 references.

References · 13

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  6. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  7. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  8. 2021Ethical and social risks of harm from Language Modelscited by 957
  9. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  10. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Modelscited by 494
  11. 2024SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Modelscited by 225
  12. 2013Stabilitycited by 119
1 more
  1. 2020Behavioral Use Licensing for Responsible AIcited by 46

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 19; 2026: 7.

34 papers.

Sort:

By area:

  1. 2025OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safetycited by 71
  2. 2024AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policiescited by 69
  3. 2025AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integrationcited by 38
  4. 2024Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Researchcited by 14
  5. 2025Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Controlcited by 14
  6. 2024Acceptable Use Policies for Foundation Modelscited by 12
  7. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  8. 2024SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behaviorcited by 10
  9. 2025MinorBench: A hand-built benchmark for content-based risks for childrencited by 8
  10. 2025Taxonomizing Representational Harms using Speech Act Theorycited by 7
  11. 2025Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMscited by 7
  12. 2025Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?cited by 6
22 more
  1. 2024Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generationcited by 5
  2. 2025Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topicscited by 5
  3. 2026BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environmentscited by 3
  4. 2024Data-Centric AI Governance: Addressing the Limitations of Model-Focused Policiescited by 2
  5. 2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systemscited by 2
  6. 2025SAIF: A Comprehensive Framework for Evaluating the Risks of Generative AI in the Public Sectorcited by 2
  7. 2025Breaking Down Bias: On The Limits of Generalizable Pruning Strategiescited by 2
  8. 2025Envisioning Stakeholder-Action Pairs to Mitigate Negative Impacts of AI: A Participatory Approach to Inform Policy Makingcited by 2
  9. 2025A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safetycited by 2
  10. 2025Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanationscited by 2
  11. 2026Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgmentcited by 2
  12. 2026Brainrot: Deskilling and Addiction are Overlooked AI Riskscited by 2
  13. 2024Standardization Trends on Safety and Trustworthiness Technology for Advanced AIcited by 0
  14. 2025ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awarenesscited by 0
  15. 2025Dimensional Characterization and Pathway Modeling for Catastrophic AI Riskscited by 0
  16. 2025Responsible AI Technical Reportcited by 0
  17. 2025Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFTcited by 0
  18. 2025Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policiescited by 0
  19. 2026No Safe Dose: How Training Data Drives Unsafe Image Generationcited by 0
  20. 2026The Eticas AI Risk Taxonomy: Open Infrastructure for Operationalizing AI Auditscited by 0
  21. 2026Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agentscited by 0
  22. 2026Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applicationscited by 0