# The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence

arXiv: https://arxiv.org/abs/2408.12622 · HTML: https://mlsanity.com/paper/2408.12622/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 52 references that are in the map.
- First posted on arXiv 14 Aug 2024.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 12 of 12)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024)
- [Evaluating the Social Impact of Generative AI Systems in Systems and Society](https://mlsanity.com/paper/2306.05949/) (2023)
- [Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem](https://mlsanity.com/paper/2310.02521/) (2023)
- [Open Source Software for Efficient and Transparent Reviews](https://mlsanity.com/paper/2006.12166/) (2020)
- [TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI](https://mlsanity.com/paper/2306.06924/) (2023)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [The Risks of Machine Learning Systems](https://mlsanity.com/paper/2204.09852/) (2022)
- [Examining the Differential Risk from High-level Artificial Intelligence and the Question of Control](https://mlsanity.com/paper/2211.03157/) (2022)

## Built on by (most cited first, 16 of 16)

- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [SHE: Trajectory-driven Safety Harness Evolution for LLM Agents](https://mlsanity.com/paper/2608.09885/) (2026)
- [Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems](https://mlsanity.com/paper/2410.23472/) (2024)
- [The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures](https://mlsanity.com/paper/2609.11030/) (2026)
- [Generative Models Erode Human Temporal Learning Through Market Selection](https://mlsanity.com/paper/2606.06572/) (2026)
- [The Eticas AI Risk Taxonomy: Open Infrastructure for Operationalizing AI Audits](https://mlsanity.com/paper/2607.02201/) (2026)
- [Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech](https://mlsanity.com/paper/2607.05165/) (2026)
- [TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems](https://mlsanity.com/paper/2607.09586/) (2026)
- [Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI](https://mlsanity.com/paper/2607.15992/) (2026)
- [An Evaluation Framework for National AI Regulation](https://mlsanity.com/paper/2608.15417/) (2026)
- [From Legal Text to AI-specific Risk Sources: A Systematic Analysis of the EU AI Act's High-Risk Requirements](https://mlsanity.com/paper/2609.13535/) (2026)
- [Mapping U.S. Federal AI Governance Against Sector Vulnerability](https://mlsanity.com/paper/2609.16260/) (2026)
- [An Open Pipeline and Dashboard for Systemic-Risk Evidence under the EU AI Act's Code of Practice](https://mlsanity.com/paper/2609.28335/) (2026)
- [Systemization of Knowledge (SoK): Human-Centered AI Safety for Youth](https://mlsanity.com/paper/2610.08554/) (2026)
- [agent-risk: Risk Assessment for Changes to AI Agents](https://mlsanity.com/paper/2610.16280/) (2026)

## Abstract (arXiv)

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks. Consider "privacy": one framework uses this term to describe a model's ability to leak sensitive training data, while another uses it to mean freedom from government surveillance. Conversely, researchers have introduced "Goodhart's law," "specification gaming," "reward hacking," and "mesa-optimization" to describe the same phenomenon of AI systems optimizing for measured proxies rather than intended goals. This terminological diversity creates friction: comparing findings across studies requires mapping between frameworks, and comprehensive risk coverage requires consulting multiple taxonomies that use different organizing principles. This paper addresses this challenge by creating a comprehensive catalog of AI risks. We systematically analyzed every major AI risk framework published to date-74 frameworks containing 1,725 distinct risks-and organized them into a unified system. Our two classification systems reveal important patterns: contrary to common assumptions, human decisions cause nearly as many AI risks (38%) as the AI systems themselves (42%). The work provides practical tools for anyone working on AI safety, from developers conducting risk assessments to policymakers writing regulations to auditors evaluating AI systems. By establishing a common reference point, this repository creates the foundation for more coordinated and comprehensive approaches to managing AI's risks while realizing its benefits.