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/

8 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

8 entries

69.03.00 · Risk Category

Information enabling malicious actions

"The chatbot shares information that can be used to do something dangerous or illegal."

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Other Post-deployment
69.04.01 · Risk Sub-Category

Bad advice/failure to generate helpful content

Harmful advice

—

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Unintentional Other
69.06.00 · Risk Category

Toxic and disrespectful content

"The chatbot verbally attacks or undermines an individual, group, or organization. 7."

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Unintentional Post-deployment
69.06.01 · Risk Sub-Category

Toxic and disrespectful content

Harasses users

-

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Other Post-deployment
69.06.03 · Risk Sub-Category

Toxic and disrespectful content

Subversive or aggressive political opinions

-

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Other Other
69.06.04 · Risk Sub-Category

Toxic and disrespectful content

Disrespectful opinions (in general)

-

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Other Other
69.09.01 · Risk Sub-Category

Forms emotional bonds

Affirms destructive thoughts and actions

—

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Other Other
69.10.00 · Risk Category

Serves as object of personal fantasy, violence, and abuse

"The chatbot participates in morally or socially objectionable conversational activities with its user that could be emotionally damaging to its user or third parties."

From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

Domain 1 1.2 AI Other Post-deployment

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