Skip to main content
This is a research prototype. The data and analyses are preliminary and not yet validated — we'd welcome your .
MIT AI Risk Initiative
BackOver- and underfitting
Poor model design choices
Lack of explainability

Over- and underfitting

AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks

Schnitzer et al. (2024)

SourceDOI
Category
Risk Domain
7AI System Safety, Failures & Limitations
7.3Lack of capability or robustness

AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

"Over- and underfitting describe the over or insufficient adaption of a model to training data. Both phenomena can cause an AI system to behave unreliably if confronted with operational data."(p. 10)

Entity: Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent: Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing: Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Other risks from Schnitzer et al. (2024) (24)

Inadequate specification of ODD

7.3 Lack of capability or robustness
HumanUnintentionalPre-deployment

Inappropriate degree of automation

7.2 AI possessing dangerous capabilities
AI systemUnintentionalPost-deployment

Inadequate planning of performance requirements

7.3 Lack of capability or robustness
HumanUnintentionalPre-deployment

Insufficient AI development documentation

7.4 Lack of transparency or interpretability
HumanOtherPre-deployment

Inappropriate degree of transparency to end users

7.4 Lack of transparency or interpretability
HumanOtherPre-deployment

Choice of untrustworthy data source

7.0 AI System Safety, Failures & Limitations
HumanUnintentionalPre-deployment
View all 24 risks from this paper →