What is the MIT AI Risk Repository?

A living database of AI risks extracted from 74 frameworks, taxonomies and papers, classified by a causal taxonomy (entity, intent, timing) and a domain taxonomy (7 domains, 24 subdomains). Published by the MIT AI Risk Initiative under CC BY 4.0.

Can I download the filtered risk list?

Yes. Apply filters and use Export CSV or Export JSON; the file carries the source, licence and citation so it can be reused with attribution.

MIT AI Risk Repository

Browse AI risks

Name: MIT AI Risk Repository: AI Risk Database (browseable copy)
Creator: MIT AI Risk Initiative
License: https://creativecommons.org/licenses/by/4.0/

72 risk entries extracted from 74 frameworks, coded by domain, subdomain, causal entity, intent and timing. Filter, then export the current selection with its licence and citation attached.

Export CSV Export JSON

72 entries · page 2 of 2

22.03.00.a · Additional evidence

Organizational Risks (Accidental)

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.03.01.a · Additional evidence

Organizational Risks (Accidental)

Accidents Are Hard to Avoid

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.03.01.b · Additional evidence

Organizational Risks (Accidental)

Accidents Are Hard to Avoid

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.03.01.c · Additional evidence

Organizational Risks (Accidental)

Accidents Are Hard to Avoid

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.03.02 · Risk Sub-Category

Organizational Risks (Accidental)

Organizational Factors can Reduce the Chances of Catastrophe

"Some organizations successfully avoid catastrophes while operating complex and hazardous systems such as nuclear reactors, aircraft carriers, and air traffic control systems [92, 93]. These organizations recognize that focusing solely on the hazards of the technology involved is insufficient; consideration must also be given to organizational factors that can contribute to accidents, including human factors, organizational procedures, and structure. These are especially important in the case of AI, where the underlying technology is not highly reliable and remains poorly understood"

From An Overview of Catastrophic AI Risks (Hendrycks2023)

Not coded Not coded Not coded
22.03.02.a · Additional evidence

Organizational Risks (Accidental)

Organizational Factors can Reduce the Chances of Catastrophe

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.00.a · Additional evidence

Rogue AIs (Internal)

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.00.b · Additional evidence

Rogue AIs (Internal)

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.00.c · Additional evidence

Rogue AIs (Internal)

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.01.a · Additional evidence

Rogue AIs (Internal)

Proxy Gaming

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.01.b · Additional evidence

Rogue AIs (Internal)

Proxy Gaming

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.02.a · Additional evidence

Rogue AIs (Internal)

Goal Drift

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.02.b · Additional evidence

Rogue AIs (Internal)

Goal Drift

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.02.c · Additional evidence

Rogue AIs (Internal)

Goal Drift

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.03.a · Additional evidence

Rogue AIs (Internal)

Power Seeking

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.03.b · Additional evidence

Rogue AIs (Internal)

Power Seeking

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.03.c · Additional evidence

Rogue AIs (Internal)

Power Seeking

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.03.d · Additional evidence

Rogue AIs (Internal)

Power Seeking

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.03.e · Additional evidence

Rogue AIs (Internal)

Power Seeking

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.03.f · Additional evidence

Rogue AIs (Internal)

Power Seeking

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.04.a · Additional evidence

Rogue AIs (Internal)

Deception

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)
22.04.04.b · Additional evidence

Rogue AIs (Internal)

Deception

—

From An Overview of Catastrophic AI Risks (Hendrycks2023)

Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.