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/

9 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

9 entries

64.01.00 · Risk Category

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

-

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.01.01 · Risk Sub-Category

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

Impersonation

"Assume the identity of a real person and take actions on their behalf"

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.01.02 · Risk Sub-Category

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

Appropriated Likeness

"Use or alter a person's likeness or other identifying features"

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.01.04 · Risk Sub-Category

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

Non-consensual intimate imagery (NCII)

"Create sexual explicit material using an adult person’s likeness"

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.01.05 · Risk Sub-Category

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

Child sexual abuse material (CSAM)

"Create child sexual explicit material"

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.02.00 · Risk Category

Misuse tactics that exploit GenAI capabilities (Realistic depictions of non-humans)

-

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.02.03 · Risk Sub-Category

Misuse tactics that exploit GenAI capabilities (Realistic depictions of non-humans)

Counterfeit

"Reproduce or imitate an original work, brand or style and pass as real"

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.03.00 · Risk Category

Misuse tactics that exploit GenAI capabilities (Use of generated content)

—

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment
64.03.02 · Risk Sub-Category

Misuse tactics that exploit GenAI capabilities (Use of generated content)

Targeting & Personalisation

"Refine outputs to target individuals with tailored attacks"

From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

Domain 4 4.3 Human Intentional Post-deployment

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.