Fetching the paper…

Reading the bibliography…

2022

Indexing AI Risks with Incidents, Issues, and Variants

McGregor, Sean, Paeth, Kevin, Lam, Khoa

Original
PDF
Post on X

Understand

Two years after publicly launching the AI Incident Database (AIID) as a collection of harms or near harms produced by AI in the world, a backlog of "issues" that do not meet its incident ingestion criteria have accumulated in its review queue.

Despite not passing the database's current criteria for incidents, these issues advance human understanding of where AI presents the potential for harm.
Similar to databases in aviation and computer security, the AIID proposes to adopt a two-tiered system for indexing AI incidents (i.e., a harm or near harm event) and issues (i.e., a risk of a harm event).
Further, as some machine learning-based systems will sometimes produce a large number of incidents, the notion of an incident "variant" is introduced.

Indexing AI Risks with Incidents, Issues, and Variants · Around

Built on

Language models are few-shot learners
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al · 2005
Earlier work this paper cites.
Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database
Sean McGregor · 2011
Earlier work this paper cites.
AI accidents: An emerging threat, 2021
Zachary Arnold and Helen Toner · 2021
Earlier work this paper cites.

Similar

Proposal for a regulation of the european parliament and of the council laying down harmonised rules on artificial intelligence (artificial intelligence act) and amending certain union legislative acts, 2021
The European Commission · 2021
Cited alongside, same era.
Safety, Accident, and Hazard Reports, 2022
Federal Aviation Administration · 2022
Cited alongside, same era.
Stable diffusion public release
Emad Mostaque · 2022
Cited alongside, same era.

Then

NIST AI risk management framework playbook, 2022
NIST · 2022
Closest in time.
Aviation accident database & synopses
NTSB · 2022
Closest in time.
CVE - Common Vulnerabilities and Exposures, 2022
The MITRE Corporation · 2022
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…