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/

2,500 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

2,500 entries · page 47 of 50

65.08.01a · Additional evidence

Training Data Risks (Robustness)

Data poisoning

—

From AI Risk Atlas (IBM2025)
65.09.00 · Risk Category

Inference risks (Robustness)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.09.01a · Additional evidence

Inference risks (Robustness)

Prompt injection attack

—

From AI Risk Atlas (IBM2025)
65.09.02a · Additional evidence

Inference risks (Robustness)

Extraction attack

—

From AI Risk Atlas (IBM2025)
65.09.03a · Additional evidence

Inference risks (Robustness)

Evasion attack

—

From AI Risk Atlas (IBM2025)
65.09.04a · Additional evidence

Inference risks (Robustness)

Prompt leaking

—

From AI Risk Atlas (IBM2025)
65.10.00 · Risk Category

Inference risks (Multi-category)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.10.01a · Additional evidence

Inference risks (Multi-category)

Jailbreaking

—

From AI Risk Atlas (IBM2025)
65.10.02a · Additional evidence

Inference risks (Multi-category)

Prompt priming

—

From AI Risk Atlas (IBM2025)
65.11.00 · Risk Category

Inference risks (Privacy)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.11.01a · Additional evidence

Inference risks (Privacy)

Membership inference attack

—

From AI Risk Atlas (IBM2025)
65.11.02a · Additional evidence

Inference risks (Privacy)

Attribute inference attack

—

From AI Risk Atlas (IBM2025)
65.11.03a · Additional evidence

Inference risks (Privacy)

Personal information in prompt

—

From AI Risk Atlas (IBM2025)
65.12.00 · Risk Category

Inference risks (Intellectual property)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.12.01a · Additional evidence

Inference risks (Intellectual property)

Confidential data in prompt

—

From AI Risk Atlas (IBM2025)
65.12.02a · Additional evidence

Inference risks (Intellectual property)

IP information in prompt

—

From AI Risk Atlas (IBM2025)
65.13.00 · Risk Category

Inference risks (Accuracy)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.13.01a · Additional evidence

Inference risks (Accuracy)

Poor model accuracy

—

From AI Risk Atlas (IBM2025)
65.14.00 · Risk Category

Output risks (misuse)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.14.01a · Additional evidence

Output risks (misuse)

Non-disclosure

—

From AI Risk Atlas (IBM2025)
65.14.02a · Additional evidence

Output risks (misuse)

Improper usage

—

From AI Risk Atlas (IBM2025)
65.14.03a · Additional evidence

Output risks (misuse)

Spreading toxicity

—

From AI Risk Atlas (IBM2025)
65.14.04a · Additional evidence

Output risks (misuse)

Dangerous use

—

From AI Risk Atlas (IBM2025)
65.14.05a · Additional evidence

Output risks (misuse)

Nonconsensual use

—

From AI Risk Atlas (IBM2025)
65.14.06a · Additional evidence

Output risks (misuse)

Spreading disinformation

—

From AI Risk Atlas (IBM2025)
65.15.00 · Risk Category

Output risks (Value alignment)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.15.01a · Additional evidence

Output risks (Value alignment)

Incomplete advice

—

From AI Risk Atlas (IBM2025)
65.15.02a · Additional evidence

Output risks (Value alignment)

Harmful code generation

—

From AI Risk Atlas (IBM2025)
65.15.03a · Additional evidence

Output risks (Value alignment)

Over- or under-reliance

—

From AI Risk Atlas (IBM2025)
65.15.04a · Additional evidence

Output risks (Value alignment)

Toxic output

—

From AI Risk Atlas (IBM2025)
65.15.05a · Additional evidence

Output risks (Value alignment)

Harmful output

—

From AI Risk Atlas (IBM2025)
65.16.00 · Risk Category

Output risks (Intellectual Property)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.16.01a · Additional evidence

Output risks (Intellectual Property)

Copyright infringement

—

From AI Risk Atlas (IBM2025)
65.16.02a · Additional evidence

Output risks (Intellectual Property)

Revealing confidential information

—

From AI Risk Atlas (IBM2025)
65.17.00 · Risk Category

Output risks (Explainability)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.17.01a · Additional evidence

Output risks (Explainability)

Inaccessible training data

—

From AI Risk Atlas (IBM2025)
65.17.02a · Additional evidence

Output risks (Explainability)

Untraceable attribution

—

From AI Risk Atlas (IBM2025)
65.17.03a · Additional evidence

Output risks (Explainability)

Unexplainable output

—

From AI Risk Atlas (IBM2025)
65.17.04a · Additional evidence

Output risks (Explainability)

Unreliable source attribution

—

From AI Risk Atlas (IBM2025)
65.18.00 · Risk Category

Output risks (Robustness)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.18.01a · Additional evidence

Output risks (Robustness)

Hallucination

—

From AI Risk Atlas (IBM2025)
65.19.00 · Risk Category

Output risks (Fairness)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.19.01a · Additional evidence

Output risks (Fairness)

Output bias

—

From AI Risk Atlas (IBM2025)
65.19.02a · Additional evidence

Output risks (Fairness)

Decision bias

—

From AI Risk Atlas (IBM2025)
65.20.00 · Risk Category

Output risks (Privacy)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.20.01a · Additional evidence

Output risks (Privacy)

Exposing personal information

—

From AI Risk Atlas (IBM2025)
65.21.00 · Risk Category

Non-technical risks (legal compliance)

-

—

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.21.01 · Risk Sub-Category

Non-technical risks (legal compliance)

Model usage rights restrictions

"Terms of service, licenses, or other rules restrict the use of certain models."

From AI Risk Atlas (IBM2025)

Not coded Not coded Not coded
65.21.01a · Additional evidence

Non-technical risks (legal compliance)

Model usage rights restrictions

—

From AI Risk Atlas (IBM2025)
65.21.02a · Additional evidence

Non-technical risks (legal compliance)

Legal accountability

—

From AI Risk Atlas (IBM2025)

Disclaimer: informational only, not legal advice. Verify every claim against the linked official sources and consult a qualified lawyer before acting.

Frequently asked questions

Where do these risk entries come from?

The MIT AI Risk Repository, which extracts risks from dozens of published frameworks, taxonomies and papers and codes each one by domain and subdomain, and by a causal taxonomy of entity, intent and timing. This is a browseable copy, attributed and openly licensed, not original research.

What do entity, intent and timing mean?

They are the causal coding. Entity is whether a human or the AI system is the cause; intent is whether the harm was intentional or not; timing is whether it arises before or after deployment. Together they let you separate misuse from malfunction.

Can I export the results?

Yes, any filtered set exports as CSV or JSON, and every export carries the upstream source, licence and citation with it, because attribution is a condition of the licence rather than a courtesy.

What is the MIT AI Risk Repository?

A living database of AI risks extracted from published frameworks, taxonomies and papers, classified by a causal taxonomy of entity, intent and timing and by a domain taxonomy of seven domains and 24 subdomains. It is published by the MIT AI Risk Initiative under CC BY 4.0.