AI Vulnerability Database (AVID)
- Type
- Public reporting channel
- Place
- International — Global
- Last checked
- 2026-09-22
- Next check due
- 2027-03-21
Ways to reach them
- Submission page
- Homepage
What it does
Failure modes in general-purpose AI systems — open-weight generative models, closed-API systems, developer tools, and end-to-end AI applications and agents. Records are split into vulnerabilities and reports, organised by a taxonomy library. Rebuilt in 2026 for agentic AI.
Honest assessment
Modest but real: it is an actively maintained, citable identifier namespace with 2026-dated records, and it is one of the few places a model-behaviour flaw can get a permanent public ID. Small organisation, small readership; do not expect it to force a vendor response on its own.
How to file
Public 'Submit an AI Vulnerability!' link on avidml.org, which routes to a Google Form. Alternatively contribute structured records via the avidml GitHub organisation. Documentation at docs.avidml.org.
Format
Structured record against AVID's taxonomy (security / ethics / performance dimensions), with reproduction detail. Short, technical, evidence-led.
Timing
Rolling.
What happens after
Accepted records get an AVID identifier (e.g. AVID-2026-R1407) and are published in the searchable database.
What it accepts
Failure modes in general-purpose AI systems — open-weight generative models, closed-API systems, developer tools, and end-to-end AI applications and agents. Records are split into vulnerabilities and reports, organised by a taxonomy library. Rebuilt in 2026 for agentic AI.
What it does not accept
Not explicitly documented. In practice it is oriented to reproducible model/system failure modes rather than narrative harm accounts — those belong in AIID.
Operated by
AI Risk and Vulnerability Alliance (ARVA), a nonprofit