MIT AI Risk Repository · Risk Sub-Category · 45.01.01

Risks from models and algorithms (Risks of explainability)

Category: AI's inherent safety risks

Description

"AI algorithms, represented by deep learning, have complex internal workings. Their black-box or grey-box inference process results in unpredictable and untraceable outputs, making it challenging to quickly rectify them or trace their origins for accountability should any anomalies arise."

From AI Safety Governance Framework (TC2602024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI
Timing
Other

Subdomain definition: Challenges in understanding or explaining the decision-making processes of AI systems, which can lead to mistrust, difficulty in enforcing compliance standards or holding relevant actors accountable for harms, and the inability to identify and correct errors.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Other entries from TC2602024